WO2021051554A1 - Certificate authenticity verification method and system, and computer device and readable storage medium - Google Patents

Abstract

A certificate authenticity verification method and system. The method comprises: acquiring an original certificate image, and identifying the certificate type of the original certificate image (S10); extracting a plurality of pieces of feature information from the original certificate image on the basis of the certificate type, parsing the plurality of pieces of feature information to obtain a plurality of pieces of target feature information, and checking the plurality of pieces of target feature information to generate a plurality of checking results (S20); and generating an authenticity verification conclusion sheet according to the plurality of checking results (S30). By means of the method, the accuracy of certificate authenticity verification is improved.

Description

证件真伪验证方法、***、计算机设备及可读存储介质Certificate authenticity verification method, system, computer equipment and readable storage medium

本申请要求于2019年9月19日提交中国专利局、申请号为201910885149.5、发明名称为“证件真伪验证方法、***、计算机设备及可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on September 19, 2019, the application number is 201910885149.5, and the invention title is "document authenticity verification method, system, computer equipment and readable storage medium", all of which The content is incorporated in this application by reference.

技术领域Technical field

本申请实施例涉及大数据领域，尤其涉及一种证件真伪验证方法、***、计算机设备及计算机可读存储介质。The embodiments of the application relate to the field of big data, and in particular to a method, system, computer equipment, and computer-readable storage medium for authenticating a certificate.

背景技术Background technique

目前，当人们在线上金融、政务、医疗等领域进行在线操作或办理业务时，往往需要对人员进行证件真伪验证，而线上的证件真伪验证依赖于远程电子证件真伪验证。At present, when people conduct online operations or conduct business in the fields of finance, government affairs, and medical treatment online, they often need to verify the authenticity of their documents, and online document authenticity verification relies on remote electronic document authenticity verification.

传统的在线办理业务时，线上的远程电子证件真伪验证方法通常依赖工作人员对获取到的原始证件图像上用户的证件信息与用户身份数据库中对应的用户证件信息进行比对，以确定证件的真伪。然而，发明人意识到传统的线上远程电子证件真伪验证方法具有以下缺陷：1、人力成本较高；2、证件真伪验证的准确率较低。When traditional online business is handled, the online remote electronic certificate authenticity verification method usually relies on the staff to compare the user's certificate information on the obtained original certificate image with the corresponding user's certificate information in the user identity database to determine the certificate The authenticity of. However, the inventor realizes that the traditional online remote electronic certificate authenticity verification method has the following defects: 1. The labor cost is high; 2. The accuracy of the certificate authenticity verification is low.

发明内容Summary of the invention

有鉴于此，本申请实施例提供了一种证件真伪验证方法、***、计算机设备及非易失性计算机可读存储介质，用于解决线上的远程电子证件真伪验证方法进行证件真伪验证准确率较低的问题。In view of this, the embodiments of the present application provide a certificate authenticity verification method, system, computer equipment, and non-volatile computer-readable storage medium, which are used to solve the online remote electronic certificate authenticity verification method for certificate authenticity. Problems with low verification accuracy.

本申请实施例是通过下述技术方案来解决上述技术问题：The embodiments of this application solve the above technical problems through the following technical solutions:

一种证件真伪验证方法，包括：A method for verifying the authenticity of a certificate, including:

获取原始证件图像，识别所述原始证件图像的证件类型；Obtain the original certificate image, and identify the certificate type of the original certificate image;

基于所述证件类型，从所述原始证件图像中提取多个特征信息，并对所述多个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果；Based on the document type, extract multiple feature information from the original document image, and analyze the multiple feature information to obtain multiple target feature information, and verify the multiple target feature information, To generate multiple verification results;

根据所述多个校验结果，以生成验真结论表单。According to the multiple verification results, a verification conclusion form is generated.

为了实现上述目的，本申请实施例还提供一种证件真伪验证***，包括：In order to achieve the foregoing objective, an embodiment of the present application also provides a certificate authenticity verification system, including:

获取模块，用于获取原始证件图像，识别所述原始证件图像的证件类型；The acquisition module is used to acquire the original certificate image and identify the certificate type of the original certificate image;

处理模块，基于所述证件类型，从所述原始证件图像中提取多个特征信息，并对所述多 个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果；The processing module, based on the document type, extracts multiple feature information from the original document image, and analyzes the multiple feature information to obtain multiple target feature information, and perform processing on the multiple target feature information Check to generate multiple check results;

结果生成模块，用于根据所述多个校验结果，以生成验真结论表单。The result generation module is used to generate a verification conclusion form according to the multiple verification results.

为了实现上述目的，本申请实施例还提供一种计算机设备，所述计算机设备包括存储器、处理器以及存储在所述存储器上并可在处理器上运行的计算机可读指令，所述处理器执行所述计算机可读指令时实现如上所述证件真伪验证方法的步骤。In order to achieve the foregoing objective, an embodiment of the present application further provides a computer device. The computer device includes a memory, a processor, and computer-readable instructions that are stored on the memory and can run on the processor, and the processor executes The computer-readable instructions implement the steps of the method for verifying the authenticity of the certificate as described above.

为了实现上述目的，本申请实施例还提供一种非易失性计算机可读存储介质，所述非易失性计算机可读存储介质内存储有计算机可读指令，所述计算机可读指令可被至少一个处理器所执行，以使所述至少一个处理器执行如上所述的证件真伪验证方法的步骤。In order to achieve the above objective, embodiments of the present application also provide a non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be Is executed by at least one processor, so that the at least one processor executes the steps of the certificate authenticity verification method as described above.

本申请实施例提供的证件真伪验证方法、***、计算机设备及非易失性计算机可读存储介质，通过识别原始证件图像的证件类型，并从原始证件图像中提取多个特征信息，且对多个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果；并根据多个校验结果判断证件的真伪，大大了提高证件真伪验证的准确性，且加快了金融、政务、医疗等领域线上业务办理时身份验证的速度。The certificate authenticity verification method, system, computer equipment, and non-volatile computer-readable storage medium provided by the embodiments of the present application recognize the certificate type of the original certificate image, and extract multiple characteristic information from the original certificate image. The multiple feature information is analyzed to obtain multiple target feature information, and the multiple target feature information is verified to generate multiple verification results; and the authenticity of the certificate is judged based on the multiple verification results, which is greatly improved Improve the accuracy of certificate authenticity verification, and accelerate the speed of identity verification during online business processing in the fields of finance, government affairs, and medical treatment.

以下结合附图和具体实施例对本申请进行详细描述，但不作为对本申请的限定。The following describes the application in detail with reference to the accompanying drawings and specific embodiments, but it is not intended to limit the application.

附图说明Description of the drawings

图1为本申请实施例一之证件真伪验证方法的步骤流程图；Figure 1 is a flow chart of the steps of the method for verifying the authenticity of a certificate in the first embodiment of this application;

图2为图1中步骤S20的具体流程示意图；FIG. 2 is a schematic diagram of a specific flow of step S20 in FIG. 1;

图3为图1中步骤S20的具体流程示意图；FIG. 3 is a schematic diagram of a specific flow of step S20 in FIG. 1;

图4为本申请实施例一之人脸比对模型训练的具体流程示意图；4 is a schematic diagram of a specific process of training a face comparison model in Embodiment 1 of the application;

图5为图1中步骤S20的具体流程示意图；FIG. 5 is a schematic diagram of a specific flow of step S20 in FIG. 1;

图6为图1中步骤S20的具体流程示意图；FIG. 6 is a schematic diagram of a specific flow of step S20 in FIG. 1;

图7为图1中步骤S20的具体流程示意图；FIG. 7 is a schematic diagram of a specific flow of step S20 in FIG. 1;

图8为图1中步骤S20的具体流程示意图；FIG. 8 is a schematic diagram of a specific flow of step S20 in FIG. 1;

图9为本申请证件真伪验证***之实施例二的程序模块示意图；9 is a schematic diagram of the program modules of the second embodiment of the authentication system for verifying the authenticity of the application certificate;

图10为本申请计算机设备之实施例三的硬件结构示意图。FIG. 10 is a schematic diagram of the hardware structure of the third embodiment of the computer equipment of this application.

具体实施方式detailed description

为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本申请，并不用于限定本申请。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。In order to make the purpose, technical solutions, and advantages of this application clearer, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not used to limit the present application. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

各个实施例之间的技术方案可以相互结合，但是必须是以本领域普通技术人员能够实 现为基础，当技术方案的结合出现相互矛盾或无法实现时应当认为这种技术方案的结合不存在，也不在本申请要求的保护范围之内。The technical solutions between the various embodiments can be combined with each other, but they must be based on what can be achieved by a person of ordinary skill in the art. When the combination of technical solutions is contradictory or cannot be achieved, it should be considered that such a combination of technical solutions does not exist. It is not within the scope of protection required by this application.

实施例一Example one

请参阅图1，示出了本申请实施例之证件真伪验证方法的步骤流程图。可以理解，本方法实施例中的流程图不用于对执行步骤的顺序进行限定。下面以计算机设备为执行主体进行示例性描述，具体如下：Please refer to FIG. 1, which shows a flowchart of the steps of a method for verifying the authenticity of a certificate according to an embodiment of the present application. It can be understood that the flowchart in this method embodiment is not used to limit the order of execution of the steps. The following is an exemplary description with computer equipment as the main body of execution, and the details are as follows:

步骤S10，获取原始证件图像，识别所述原始证件图像的证件类型。Step S10: Obtain an original certificate image, and identify the certificate type of the original certificate image.

其中，证件类型是指与原始证件图像对应的类型，其证件类型可以为二代居民身份证、香港身份证、港澳通行证和护照等。Among them, the document type refers to the type corresponding to the original document image, and the document type can be a second-generation resident ID card, a Hong Kong ID card, a Hong Kong and Macau pass, a passport, etc.

具体地，计算机设备获取用户端发送的原始证件图像，所述原始证件图像对应的证件类型可以是用户端在上传原始证件图像时确定的证件类型；所述原始证件图像对应的证件类型也可以是计算机设备通过图像识别技术识别所述原始证件图像的版式，以根据相应的版式匹配所述原始证件图像的证件类型。Specifically, the computer device obtains the original certificate image sent by the client, and the certificate type corresponding to the original certificate image may be the certificate type determined by the client when uploading the original certificate image; the certificate type corresponding to the original certificate image may also be The computer equipment recognizes the format of the original document image through image recognition technology, so as to match the certificate type of the original document image according to the corresponding format.

步骤S20，基于所述证件类型，从所述原始证件图像中提取多个特征信息，并对所述多个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果。Step S20: Based on the document type, extract a plurality of characteristic information from the original document image, and analyze the plurality of characteristic information to obtain a plurality of target characteristic information, and perform processing on the plurality of target characteristic information. Check to generate multiple check results.

具体的，所述多个特征信息包括多个特征向量序列及多个图像区域；所述多个目标特征信息包括对应的文字特征向量序列及图像区域数据。Specifically, the multiple feature information includes multiple feature vector sequences and multiple image regions; the multiple target feature information includes corresponding text feature vector sequences and image region data.

在示例性的实施例中，请参阅图2，步骤S20还可以进一步包括：In an exemplary embodiment, referring to FIG. 2, step S20 may further include:

步骤S200A，对所述原始证件图像进行定位，以获取多个特征向量序列及所述多个特征向量序列对应的多个位置标识。Step S200A: Position the original document image to obtain multiple feature vector sequences and multiple location identifiers corresponding to the multiple feature vector sequences.

其中，位置标识是指与特征向量序列对应的标识，通过该位置标识可查找到对应的特征向量序列；例如，某一香港身份证号的位置标识为1，通过位置标识1可定位该特征向量序列为香港身份证号区域；某一香港身份证的标准人像区域(即香港身份证上大人像的区域)的位置标识为2，通过位置标识2可定位该特征向量序列为标准人像区域。Among them, the location identification refers to the identification corresponding to the feature vector sequence, through which the corresponding feature vector sequence can be found; for example, the location identification of a certain Hong Kong ID card number is 1, and the feature vector can be located through the location identification 1. The sequence is the Hong Kong ID card number area; the standard portrait area of a Hong Kong ID card (ie, the area of the adult portrait on the Hong Kong ID card) has a location identifier of 2, and the feature vector sequence can be located as a standard portrait area through the location identifier 2.

示例性的，可以采用CNN-BLSTM模型对所述原始证件图像进行定位、解析。Exemplarily, the CNN-BLSTM model may be used to locate and analyze the original document image.

其中，CNN(Convolutional Neural Networks，卷积神经网络，以下简称CNN)模型是用于提取图像特征的模型。BLSTM(双向长短期记忆，Bi-directional long-short term memory，以下简称BLSTM)模型是用于处理序列数据的模型。通过将CNN模型无缝结合到BLSTM模型中，以完成文字的校验。Among them, the CNN (Convolutional Neural Networks, convolutional neural network, hereinafter referred to as CNN) model is a model for extracting image features. The BLSTM (Bi-directional long-short term memory, hereinafter referred to as BLSTM) model is a model for processing sequence data. By seamlessly integrating the CNN model into the BLSTM model, the text verification is completed.

具体的，CNN-BLSTM模型包括输入层、卷积层、池化层、全连接层、BLSTM层、输出层等，其中，BLSTM层由两个单独的LSTM层组成。Specifically, the CNN-BLSTM model includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, a BLSTM layer, an output layer, etc., where the BLSTM layer is composed of two separate LSTM layers.

将所述原始证件图像输入至CNN-BLSTM模型的输入层中；卷积层对输入层的所述原始证 件图像进行卷积操作，以得到多个卷积特征图；池化层对所述多个卷积特征图进行池化操作，以得到降维后的多个卷积特征图；全连接层将降维后的多个卷积特征图中的多个卷积特征转化为对应的多个特征向量序列；BLSTM层对多个特征向量序列的每一帧进行预测操作，以获取多个特征向量序列对应的位置坐标关系；基于多个位置坐标关系以及预设规则，输出层输出多个特征向量序列及多个特征向量序列对应的位置标识。The original document image is input into the input layer of the CNN-BLSTM model; the convolutional layer performs convolution operation on the original document image of the input layer to obtain multiple convolution feature maps; the pooling layer performs the convolution operation on the original document image of the input layer; Perform pooling operations on multiple convolution feature maps to obtain multiple convolution feature maps after dimensionality reduction; the fully connected layer converts multiple convolution features in the multiple convolution feature maps after dimensionality reduction into multiple corresponding ones Feature vector sequence; the BLSTM layer performs prediction operations on each frame of multiple feature vector sequences to obtain the position coordinate relationships corresponding to multiple feature vector sequences; based on multiple position coordinate relationships and preset rules, the output layer outputs multiple features Position identification corresponding to the vector sequence and multiple feature vector sequences.

步骤S200B，从所述多个特征向量序列中提取多个文字特征向量序列。Step S200B, extracting multiple character feature vector sequences from the multiple feature vector sequences.

步骤S200C，基于所述证件类型，对所述多个文字特征向量序列进行识别操作，以获取所述多个文字特征向量序列对应的多个目标文字。In step S200C, a recognition operation is performed on the plurality of character feature vector sequences based on the certificate type to obtain a plurality of target characters corresponding to the plurality of character feature vector sequences.

具体的，所述目标文字可以包括中文、数字和英文等。Specifically, the target text may include Chinese, numbers, English, etc.

步骤S200D，基于所述证件类型及多个位置标识，获取与所述证件类型对应的多个预设的文字内容规则。Step S200D, based on the certificate type and multiple location identifiers, obtain a plurality of preset text content rules corresponding to the certificate type.

其中，预设的文字内容规则是指预先设置的针对每一证件类型对应的目标文字进行校验的规则。Among them, the preset text content rule refers to a preset rule for verifying the target text corresponding to each certificate type.

在本申请实施例中，多个所述文字内容规则可以是依据证件标准规则预先编写的代码，通过执行该代码对相应的目标文字进行校验。证件标准规则是国家制定的关于证件标准的规则。In the embodiment of the present application, a plurality of the text content rules may be pre-written codes according to the certificate standard rules, and the corresponding target texts are verified by executing the codes. The certificate standard rules are the rules on certificate standards formulated by the state.

具体的，计算机设备中存储有每一证件类型对应的数据库，其数据库中包含有所有用户的证件对应的文字内容规则及与文字内容规则相关的标准文字。计算机设备通过证件类型查找相应的数据库，获取与证件类型对应的数据库，通过多个位置标识获取对应的文字内容规则，再通过文字内容规则获取相应的目标文字。Specifically, a database corresponding to each certificate type is stored in the computer device, and the database contains the text content rules corresponding to all the user's certificates and standard text related to the text content rules. The computer device searches the corresponding database according to the certificate type, obtains the database corresponding to the certificate type, obtains the corresponding text content rule through multiple location identifiers, and then obtains the corresponding target text through the text content rule.

在示例性的实施例中，证件类型为香港身份证时，查找香港身份证对应的数据库，其香港身份证对应的数据库中包含依据证件标准规则预先编写的对香港身份证进行校验的文字内容规则。香港身份证号包括三部分：一个或两个英文字母；六个数字；括弧及括弧内0-9中的任一个数字或者括弧内的字母A。其中，括弧内的数字或者字母A为查核用数码，该查核用数码用来校验前面的数字是否正确。In an exemplary embodiment, when the document type is a Hong Kong ID card, the database corresponding to the Hong Kong ID card is searched, and the database corresponding to the Hong Kong ID card contains text content for verifying the Hong Kong ID card prepared in advance according to the document standard rules. rule. The Hong Kong ID card number consists of three parts: one or two English letters; six numbers; brackets and any number from 0-9 in the brackets or the letter A in the brackets. Among them, the number or letter A in the brackets is the number for verification, and the number for verification is used to verify whether the preceding number is correct.

根据香港身份证的文字内容规则，香港身份证号“一个或两个英文字母”部分可以用数字代表，即A以1代表，B以2代表...Z以26代表，再将“一个或两个英文字母”部分代表的数字乘以8，六个数字中的第一个数字乘以7，六个数字中的第二个数字乘以6，依此类推，六个数字中的第六个数字乘以2，再将以上所有乘积相加，得到一个数，再将这个数除以11，得到余数。如果整除，括弧内的查核用数码为0；如果余数为1，则括弧内的查核用数码为A；如果余数为2～10，则用11减去这个余数的差，即为括弧内的查核用数码。According to the text content rules of the Hong Kong ID card, the “one or two English letters” part of the Hong Kong ID card number can be represented by numbers, that is, A is represented by 1, B is represented by 2... Z is represented by 26, and then “one or The number represented by the "two English letters" part is multiplied by 8, the first number of the six numbers is multiplied by 7, the second number of the six numbers is multiplied by 6, and so on, the sixth of the six numbers Multiply a number by 2, then add all the above products together to get a number, and then divide this number by 11 to get the remainder. If divisible, the check number in parentheses is 0; if the remainder is 1, then the check number in parentheses is A; if the remainder is 2-10, the difference of the remainder is subtracted from 11, which is the check in parentheses Use digital.

进一步地，根据证件的类型和版式的差异，证件的不同位置对应的文字内容规则不同。在示例性的实施例中，香港身份证中包含中文电码、中文名称、签发日期、标记符号、首次签发日期、英文名、出生日期、性别和身份id等区域，每一区域对应一位置标识，则通过 位置标识可在与香港身份证对应的数据库中查找到对应的文字内容规则。如，在香港身份证对应的数据库中，通过中文电码的位置标识可查找到与中文电码区域对应的文字内容规则。Further, according to the type and format of the certificate, the text content rules corresponding to different positions of the certificate are different. In an exemplary embodiment, the Hong Kong ID card contains areas such as Chinese code, Chinese name, date of issuance, marking symbols, date of first issuance, English name, date of birth, gender, and identity id, and each area corresponds to a location identifier. Then, the corresponding text content rules can be found in the database corresponding to the Hong Kong ID card through the location identification. For example, in the database corresponding to the Hong Kong ID card, the text content rules corresponding to the Chinese code area can be found through the location identification of the Chinese code.

步骤S200E，基于所述证件类型及多个所述文字内容规则，对所述多个目标文字进行校验，以生成文字校验结果。In step S200E, the multiple target texts are verified based on the certificate type and the multiple text content rules to generate a text verification result.

具体的，接上例，根据文字内容规则获取相应的标准文字，再基于证件类型将目标文字与标准文字进行匹配，以生成文字校验结果，其中，文字校验结果可为校验成功或校验失败。Specifically, following the above example, the corresponding standard text is obtained according to the text content rules, and then the target text is matched with the standard text based on the certificate type to generate a text verification result, where the text verification result can be a successful verification or a proofreading The test failed.

当任一目标文字与相应的标准文字匹配不成功，则判定文字校验结果为校验失败；当所有目标文字均与相应的标准文字匹配成功，则判定文字校验结果为校验成功。When any target text fails to match the corresponding standard text, it is determined that the text verification result is a verification failure; when all target texts match the corresponding standard text successfully, the text verification result is determined to be a verification success.

在本申请实施例中，还可以基于所述证件类型，根据多个预设的防伪标签从所述原始证件图像中提取多个图像区域，并对所述多个图像区域进行解析，以获取多个图像区域数据，再对多个图像区域数据进行校验，以生成多个图像校验结果。In the embodiment of the present application, it is also possible to extract multiple image areas from the original document image based on the document type according to multiple preset anti-counterfeiting labels, and analyze the multiple image areas to obtain multiple Multiple image area data, and then verify multiple image area data to generate multiple image verification results.

其中，多个图像校验结果可以为校验成功或校验失败。Among them, multiple image verification results may be verification success or verification failure.

具体的，不同的证件类型预先配置有预设的防伪标签。在示例性的实施例中，以香港身份证为例，多个预设的防伪标签包括：身份证标准人像(大人像区域)、持证人照片、彩虹印刷、多元化图案背景、光学变色油墨三角形、具波浪及立体效果的全息图、微缩文字印刷、透明窗等。Specifically, different certificate types are pre-configured with preset anti-counterfeiting labels. In an exemplary embodiment, taking a Hong Kong ID card as an example, a plurality of preset anti-counterfeiting labels include: ID card standard portrait (adult portrait area), photo of the holder, rainbow printing, diversified pattern background, optical color-changing ink Triangles, holograms with wave and three-dimensional effects, micro-text printing, transparent windows, etc.

在香港身份证对应的数据库中，每个用户的证件的多个图像区域具有预设的防伪标签。计算机设备通过证件类型查找相应的数据库，获取与证件类型对应的数据库，并从该数据库中获取多个防伪标签，根据多个防伪标签与原始证件图像各图像区域进行匹配，获取匹配成功对应的图像区域。例如，防伪标签为身份证标准人像，将该防伪标签与原始证件图像中的各个图像区域进行匹配，若某个图像区域与香港身份证对应的数据库中具有身份证标准人像标签的身份证标准人像区域匹配成功，则为该图像区域匹配身份证标准人像标签，并从所述原始证件图像中提取该图像区域。In the database corresponding to the Hong Kong ID card, multiple image areas of each user's ID have preset anti-counterfeiting labels. The computer equipment searches the corresponding database by the certificate type, obtains the database corresponding to the certificate type, and obtains multiple anti-counterfeit labels from the database, matches the multiple anti-counterfeit labels with each image area of the original document image, and obtains the image corresponding to the successful match area. For example, if the anti-counterfeiting label is an ID standard portrait, the anti-counterfeiting label is matched with each image area in the original ID image. If a certain image region corresponds to a Hong Kong ID card in the database with the ID standard portrait label, the ID standard portrait If the area matching is successful, the image area matches the ID standard portrait label, and the image area is extracted from the original document image.

在本申请实施例中，计算机设备获取的原始证件图像包括证件正面拍摄图像和至少两个证件侧面拍摄图像。其中，所述证件正面拍摄图像包括垂直于证件拍摄的证件正面图像和证件背面图像；所述证件侧面拍摄图像包括以证件正面拍摄图像为基准，通过预设角度倾斜拍摄的证件正面图像和证件背面图像，预设角度可以为20-50度之间。In this embodiment of the present application, the original document image acquired by the computer device includes a front-side photograph image of the document and at least two side-side photograph images of the document. Wherein, the image taken on the front of the document includes a front image of the document and an image of the back of the document taken perpendicular to the document; the image taken from the side of the document includes the image of the front of the document and the image of the back of the document taken obliquely at a preset angle. For the image, the preset angle can be between 20-50 degrees.

在示例性的实施例中，请参阅图3，步骤S20还可以进一步包括：In an exemplary embodiment, referring to FIG. 3, step S20 may further include:

步骤S210，根据预设的防伪标签从所述证件正面拍摄图像提取持证人照片人像区域及标准人像区域。Step S210, extracting a portrait area and a standard portrait area of the holder's photo from the image taken on the front of the document according to a preset anti-counterfeiting label.

具体的，根据相应的身份证标准人像(大人像区域)及持证人照片的防伪标签，根据标准矩形的尺寸裁剪所述证件正面拍摄图像，裁剪后的证件正面拍摄图像包含持证人照片人像区域及标准人像区域。Specifically, according to the corresponding ID card standard portrait (adult portrait area) and the anti-counterfeiting label of the holder's photo, crop the front-side shot image of the document according to the size of the standard rectangle, and the cropped front-side shot image contains the holder's photo portrait. Area and standard portrait area.

步骤S211，将所述持证人照片人像区域与标准人像区域进行匹配，以获取人脸校验结果： 当持证人照片人像区域与标准人像区域匹配一致时，则判定所述人脸校验结果为校验成功；当持证人照片人像区域与标准人像区域匹配不一致时，则判定人脸校验结果为校验失败。Step S211, matching the portrait area of the holder's photo with the standard portrait area to obtain the face verification result: When the portrait area of the holder's photo matches the standard portrait area, it is determined that the face verification is The result is that the verification is successful; when the portrait area of the holder's photo is inconsistent with the standard portrait area, the face verification result is determined to be a verification failure.

具体的，采用人脸比对模型对持证人照片人像区域与标准人像区域进行匹配；其中，人脸比对模型可以为经过训练后的第一神经网络模型。Specifically, a face comparison model is used to match the portrait area of the holder's photo with the standard portrait area; wherein, the face comparison model may be a trained first neural network model.

请参阅图4，本申请实施例还包括对第一神经网络模型的训练步骤。Referring to FIG. 4, the embodiment of the present application further includes a training step of the first neural network model.

步骤S2111，初始化预配置的第一神经网络模型的多个参数；Step S2111, initialize multiple parameters of the pre-configured first neural network model;

步骤S2112，从香港身份证对应的数据库中获取多个用户的多个样本数据，所述多个样本数据包括多个用户的标准人像区域和持证人照片人像区域；Step S2112: Obtain multiple sample data of multiple users from the database corresponding to the Hong Kong ID card, the multiple sample data including the standard portrait area of the multiple users and the photo portrait area of the holder;

步骤S2113，通过多个样本数据训练第一神经网络模型，并不断调整多个参数，以得到人脸比对模型。In step S2113, the first neural network model is trained through multiple sample data, and multiple parameters are continuously adjusted to obtain a face comparison model.

在示例性的实施例中，请参阅图5，步骤S20还可以进一步包括：In an exemplary embodiment, referring to FIG. 5, step S20 may further include:

步骤S220，根据预设的防伪标签从所述证件正面拍摄图像中提取目标彩虹印刷区域。Step S220: Extract the target rainbow printing area from the photographed image on the front of the document according to the preset anti-counterfeiting label.

具体的，根据相应的彩虹印刷防伪标签，根据标准矩形的尺寸裁剪所述证件正面拍摄图像，裁剪后的证件正面拍摄图像包含目标彩虹印刷区域。Specifically, according to the corresponding rainbow printed anti-counterfeiting label, the front-side photographed image of the certificate is cropped according to the size of the standard rectangle, and the cropped front-side photographed image of the certificate contains the target rainbow printing area.

步骤S221，获取目标彩虹印刷区域的整体颜色渐变风格与标准证件的整体颜色渐变风格的第一相似度。Step S221: Obtain the first degree of similarity between the overall color gradient style of the target rainbow printing area and the overall color gradient style of the standard document.

具体的，将经裁剪后且包含目标彩虹印刷区域的证件正面拍摄图像输入至第二神经网络模型中，以通过所述第二神经网络模型输出目标彩虹印刷区域的整体颜色渐变风格与标准证件的标准颜色渐变风格的第一相似度。Specifically, the cropped frontal photographed image of the document containing the target rainbow printing area is input into the second neural network model, so as to output the overall color gradient style of the target rainbow printing area and the standard document through the second neural network model. The first similarity of the standard color gradient style.

本申请实施例还包括对所述第二神经网络模型的训练过程：The embodiment of the application also includes a training process for the second neural network model:

从香港身份证对应的数据库中获取多个合规香港身份证图片和不合规香港身份证图片；将所述多个合规香港身份证图片(即标准香港身份证图片)和不合规香港身份证图片输入至第二神经网络模型中，通过所述第二神经网络模型将所述多个合规香港身份证图片和不合规香港身份证图片不断进行训练和分类，直至合规香港身份证图片归类至正样本图片的分类类别中，不合规香港身份证图片归类至负样本图片的分类类别中。经过训练后的第二神经网络模型就会保存有合规香港身份证图片的彩虹印刷区域的标准颜色渐变风格的特征。Obtain multiple compliant Hong Kong ID images and non-compliant Hong Kong ID images from the database corresponding to the Hong Kong ID card; combine the multiple compliant Hong Kong ID images (ie, standard Hong Kong ID images) and non-compliant Hong Kong ID images The ID card image is input into the second neural network model, and the multiple compliant Hong Kong ID card images and non-compliant Hong Kong ID card images are continuously trained and classified through the second neural network model until the Hong Kong identity is compliant The image of the certificate is classified into the classification category of the positive sample image, and the non-compliant Hong Kong ID card image is classified into the classification category of the negative sample image. After training, the second neural network model will save the features of the standard color gradient style of the rainbow printing area of the compliant Hong Kong ID card image.

步骤S222，将所述第一相似度与预设的第一阈值进行对比，以获取整体颜色渐变风格校验结果；当所述第一相似度高于所述第一阈值时，则判定整体颜色渐变风格校验结果为校验成功；当所述第一相似度低于所述第一阈值时，则判定整体颜色渐变风格校验结果为校验失败。Step S222: Compare the first similarity with a preset first threshold to obtain an overall color gradient style verification result; when the first similarity is higher than the first threshold, determine the overall color The gradient style verification result is a successful verification; when the first similarity is lower than the first threshold, it is determined that the overall color gradient style verification result is a verification failure.

在示例性的实施例中，请参阅图6，步骤S20还可以进一步包括：In an exemplary embodiment, referring to FIG. 6, step S20 may further include:

步骤S230，根据预设的防伪标签从至少两个所述证件侧面拍摄图像中提取目标多元化图案背景区域。Step S230: Extract a target diversified pattern background area from at least two images taken from the side of the document according to a preset anti-counterfeiting label.

具体的，根据相应的多元化图案背景防伪标签，根据标准矩形的尺寸裁剪所述证件侧面 拍摄图像，裁剪后的证件侧面拍摄图像包含目标彩虹印刷区域。Specifically, according to the corresponding diversified pattern background anti-counterfeiting label, the side-shot image of the certificate is cropped according to the size of the standard rectangle, and the cropped side-side image of the certificate contains the target rainbow printing area.

步骤S231，获取目标多元化图案背景区域与标准证件的多元化图案背景区域的第二相似度。Step S231: Obtain a second degree of similarity between the target plural pattern background area and the plural pattern background area of the standard certificate.

具体的，将多个裁剪后切包含目标多元化图案背景区域的证件侧面拍摄图像输入至第一卷积神经网络模型中，以通过所述第一卷积神经网络模型输出目标多元化图案背景区域与标准证件的多元化图案背景区域的第二相似度。Specifically, a plurality of cropped and cut images of the side of the document containing the target diversified pattern background area are input into the first convolutional neural network model to output the target diversified pattern background area through the first convolutional neural network model The second degree of similarity with the background area of the diversified pattern of the standard document.

其中，所述第一卷积神经网络模型包括12个卷积层、2个池化层、2个全连接层、sigmod激活函数等。Wherein, the first convolutional neural network model includes 12 convolutional layers, 2 pooling layers, 2 fully connected layers, sigmod activation function, and so on.

进一步地，将多个裁剪后切包含目标多元化图案背景区域的证件侧面拍摄图像输入至第一卷积神经网络模型中，以通过12个卷积层进行卷积操作、池化操作、降维操作等输出一个处于[0，1]区间的第二相似度。Further, input multiple cropped images from the side of the document containing the target diversified pattern background area into the first convolutional neural network model to perform convolution operation, pooling operation, and dimensionality reduction through 12 convolutional layers Operation and so on output a second similarity in the interval [0, 1].

由于该第一卷积神经网络模型训练时，标注正样本证件图片的输出值为1，负样本证件图片的输出值为0，网络拟合趋向的结果是使正样本趋近1，负样本趋近0，所以将第一卷积神经网络模型输出的输出值就可以认为是符合正样本证件图片的第二相似度。Since the first convolutional neural network model is trained, the output value of the positive sample ID picture is 1 and the output value of the negative sample ID picture is 0. The result of the network fitting trend is that the positive sample approaches 1 and the negative sample tends to It is close to 0, so the output value of the first convolutional neural network model can be regarded as conforming to the second similarity of the positive sample ID picture.

步骤S232，将所述第二相似度与预设的第二阈值进行对比，以获取多元化图案背景校验结果；当所述第二相似度高于所述第二阈值，则判定多元化图案背景校验结果为校验成功；当所述第二相似度低于所述第二阈值，则判定多元化图案背景校验结果为校验失败。Step S232, comparing the second similarity with a preset second threshold to obtain a multi-pattern background check result; when the second similarity is higher than the second threshold, determining the multi-pattern The background check result is a successful check; when the second similarity is lower than the second threshold, it is determined that the background check result of the plural pattern is a check failed.

在示例性的实施例中，请参阅图7，步骤S20还可以进一步包括：In an exemplary embodiment, referring to FIG. 7, step S20 may further include:

步骤S240，根据预设的防伪标签从至少两个所述证件侧面拍摄图像中提取多个目标光学变色油墨三角形区域与多个目标具波浪及立体效果的全息图区域。Step S240, extracting a plurality of target optically color-changing ink triangle regions and a plurality of target hologram regions with wave and three-dimensional effects from at least two images taken from the side of the document according to a preset anti-counterfeiting label.

具体的，根据相应的光学变色油墨三角形防伪标签与具波浪及立体效果的全息图防伪标签，根据标准矩形的尺寸裁剪至少两个所述证件侧面拍摄图像，裁剪后的证件侧面拍摄图像包含目标光学变色油墨三角形区域与目标具波浪及立体效果的全息图区域。Specifically, according to the corresponding optically color-changing ink triangular anti-counterfeiting label and the holographic anti-counterfeiting label with wave and three-dimensional effects, at least two of the side-shot images of the document are cropped according to the size of the standard rectangle, and the cropped side-side image of the document contains the target optics. The triangle area of the color-changing ink and the hologram area of the target with wave and three-dimensional effect.

进一步的，所述证件侧面拍摄图像有两个，基于光学变色油墨三角形防伪标签定位光学变色油墨三角形区域的位置，从两个证件侧面拍摄图像中提取出目标光学变色油墨三角形区域；所述目标光学变色油墨三角形区域包括第一光学变色油墨三角形区域和第二光学变色油墨三角形区域。Further, there are two photographed images from the side of the document, and the position of the triangular area of the optical color-changing ink is located based on the triangular anti-counterfeiting label of the optical color-changing ink, and the triangular area of the target optical color-changing ink is extracted from the two photographed images on the side of the document; the target optics The color changing ink triangular area includes a first optical color changing ink triangular area and a second optical color changing ink triangular area.

在本申请实施例中，由于具波浪及立体效果的全息图区域需要通过不同拍摄角度进行判断，从香港身份证对应的数据库中获取多个不同角度拍摄的合规香港身份证图片和不合规香港身份证图片；将上述多个合规香港身份证图片(即标准香港身份证图片)和不合规香港身份证图片输入至第二卷积神经网络模型中进行训练，并综合不同拍摄角度的香港身份证图片对应的判断结果以获取最终的判断结果。因此，经过训练后的第二卷积神经网络模型保存有多个不同角度的标准证件的具波浪及立体效果的全息图的特征。In the embodiment of this application, since the hologram area with wave and three-dimensional effect needs to be judged by different shooting angles, multiple compliant Hong Kong ID card pictures taken from different angles and non-compliant are obtained from the database corresponding to the Hong Kong ID card. Hong Kong ID card image; input the above multiple compliant Hong Kong ID card images (ie standard Hong Kong ID card images) and non-compliant Hong Kong ID card images into the second convolutional neural network model for training, and integrate different shooting angles The judgment result corresponding to the Hong Kong ID card picture is used to obtain the final judgment result. Therefore, the trained second convolutional neural network model saves the characteristics of holograms with waves and three-dimensional effects of standard documents from different angles.

步骤S241，获取目标光学变色油墨三角形区域与标准证件的光学变色油墨三角形区域的 第三相似度以及目标具波浪及立体效果的全息图区域与标准证件的具波浪及立体效果的全息图区域的第四相似度。Step S241: Obtain the third degree of similarity between the triangular area of the target optical color-changing ink and the triangular area of the optical color-changing ink of the standard document, and the third similarity between the hologram area of the target with wave and three-dimensional effect and the hologram area of the standard document with wave and three-dimensional effect. Four similarities.

具体的，将第一光学变色油墨三角形区域和第二光学变色油墨三角形区域输入到第三神经网络模型中，通过第三神经网络模型输出目标光学变色油墨三角形区域与标准证件的光学变色油墨三角形区域的第三相似度。Specifically, the first optical color-changing ink triangle area and the second optical color-changing ink triangle area are input into the third neural network model, and the target optical color-changing ink triangle area and the optical color-changing ink triangle area of the standard certificate are output through the third neural network model. The third degree of similarity.

具体的，将多个目标具波浪及立体效果的全息图区域输入至第二卷积神经网络模型中，以通过所述第二卷神经网络模型输出目标具波浪及立体效果的全息图区域与标准证件的具波浪及立体效果的全息图区域的第四相似度。Specifically, the multiple target hologram areas with wave and three-dimensional effects are input into the second convolutional neural network model, and the target hologram area with wave and three-dimensional effects and standards are output through the second volume neural network model. The fourth degree of similarity of the hologram area with waves and three-dimensional effects of the certificate.

步骤S242，将所述第三相似度与预设的第三阈值进行对比，将所述第四相似度与预设的第四阈值进行对比，以获取背景图案校验结果；当第三相似度高于所述第三阈值，且所述第四相似度高于所述第四阈值；则判定背景图案校验结果为校验成功；当第三相似度低于所述第三阈值和/或所述第四相似度低于所述第四阈值；则判定背景图案校验结果为校验失败。Step S242, comparing the third similarity with a preset third threshold, and comparing the fourth similarity with a preset fourth threshold to obtain a background pattern verification result; when the third similarity is Higher than the third threshold, and the fourth similarity is higher than the fourth threshold; then it is determined that the background pattern verification result is a successful verification; when the third similarity is lower than the third threshold and/or The fourth degree of similarity is lower than the fourth threshold; then it is determined that the background pattern verification result is a verification failure.

在示例性的实施例中，请参阅图8，步骤S20还可以进一步包括：In an exemplary embodiment, referring to FIG. 8, step S20 may further include:

步骤S250，根据预设的防伪标签从所述证件正面拍摄图像中提取目标微缩文字印刷区域及目标透明窗区域，所述目标透明窗区域包括用户个人资料。Step S250, extracting a target microtext printing area and a target transparent window area from the photographed image on the front of the document according to a preset anti-counterfeiting label, where the target transparent window area includes the user's personal data.

具体的，根据相应的微缩文字印刷防伪标签与透明窗防伪标签，根据标准矩形的尺寸裁剪所述证件正面拍摄图像，裁剪后的证件侧面拍摄图像包含目标微缩文字印刷区域及目标透明窗区域。Specifically, the anti-counterfeiting label and the transparent window anti-counterfeiting label are printed according to the corresponding micro-text, and the front-side photographed image of the document is cropped according to the size of a standard rectangle. The cut-out side-side photographed image of the certificate includes the target micro-text printing area and the target transparent window area.

步骤S251，将所述目标微缩文字印刷区域进行放大操作，以得到放大后的目标微缩文字印刷区域。Step S251, performing an enlargement operation on the target micro-text printing area to obtain an enlarged target micro-text printing area.

步骤S252，获取目标微缩文字印刷区域与标准证件的微缩文字印刷区域的第五相似度以及目标透明窗区域与证件类型对应的数据库中对应的用户个人资料的第六相似度。Step S252: Obtain the fifth similarity between the target micro-text printing area and the micro-text printing area of the standard certificate and the sixth similarity between the target transparent window area and the corresponding user profile in the database corresponding to the certificate type.

具体的，将放大后的目标微缩文字印刷区域输入至第四神经网络模型中，以通过第四神经网络模型输出目标微缩文字印刷区域与标准证件的微缩文字印刷区域的第五相似度。Specifically, the enlarged target micro-text printing area is input into the fourth neural network model to output the fifth similarity between the target micro-text printing area and the micro-text printing area of the standard certificate through the fourth neural network model.

将目标透明窗区域输入至第五神经网络模型中，以通过第五神经网络模型输出目标透明窗区域与香港身份证对应的数据库中对应的用户个人资料的第六相似度。The target transparent window area is input into the fifth neural network model to output the sixth similarity between the target transparent window area and the corresponding user personal data in the database corresponding to the Hong Kong ID card through the fifth neural network model.

步骤S253，将所述第五相似度与预设的第五阈值进行比对，将所述第六相似度与预设的第六阈值进行比对，以获取内容校验结果；当所述第五相似度高于所述第五阈值，且所述第六相似度高于所述第六阈值时，判定内容校验结果为校验成功；当第五相似度低于所述第五阈值和/或所述第六相似度低于所述第六阈值，则判定内容图案校验结果为校验失败。Step S253, comparing the fifth similarity with a preset fifth threshold, and comparing the sixth similarity with a preset sixth threshold to obtain a content verification result; When the five similarity is higher than the fifth threshold, and the sixth similarity is higher than the sixth threshold, it is determined that the content verification result is a successful verification; when the fifth similarity is lower than the fifth threshold and /Or the sixth similarity is lower than the sixth threshold, it is determined that the content pattern verification result is a verification failure.

步骤S30，根据所述多个校验结果，以生成验真结论表单。In step S30, a verification conclusion form is generated according to the multiple verification results.

具体的，当文字校验结果、人脸校验结果、变色油墨校验结果、整体颜色渐变风格校验结果、多元化图案背景校验结果、背景图案校验结果及内容校验结果均为校验成功时，则所述原始证件图像对应的证件为合规证件；根据最终的校验结果，生成验真结论表单，并将 所述原始证件图像对应的证件为合规证件的结论数据填入所述验真结论表单中。Specifically, when text verification results, face verification results, color-changing ink verification results, overall color gradient style verification results, multiple pattern background verification results, background pattern verification results, and content verification results are all verified When the verification is successful, the document corresponding to the original document image is a compliance document; according to the final verification result, a verification conclusion form is generated, and the document corresponding to the original document image is filled in with the conclusion data of the compliance document The verification conclusion form.

当文字校验结果、人脸校验结果、变色油墨校验结果、整体颜色渐变风格校验结果、多元化图案背景校验结果、背景图案校验结果及内容校验结果中的任一校验结果为校验失败时，则所述原始证件图像对应的证件为不合规证件；根据最终的校验结果，生成验真结论表单，并将所述原始证件图像对应的证件为不合规证件的结论数据填入所述验真结论表单中。When any of text verification results, face verification results, color change ink verification results, overall color gradient style verification results, multiple pattern background verification results, background pattern verification results, and content verification results are verified When the result is that the verification fails, the document corresponding to the original document image is a non-compliant document; according to the final verification result, a verification conclusion form is generated, and the document corresponding to the original document image is a non-compliant document The conclusion data of is filled in the truth-verification conclusion form.

在示例性的实施例中，根据最终的校验结果将该原始证件图像保存到香港身份证对应的数据库中，并对该原始证件图像进行分类。In an exemplary embodiment, the original document image is saved in the database corresponding to the Hong Kong ID card according to the final verification result, and the original document image is classified.

进一步地，将所述验真结论表单返回至用户端。Further, the verification conclusion form is returned to the user terminal.

实施例二Example two

请继续参阅图9，示出了本申请证件真伪验证***的程序模块示意图。在本申请实施例中，证件真伪验证***20可以包括或被分割成一个或多个程序模块，一个或者多个程序模块被存储于存储介质中，并由一个或多个处理器所执行，以完成本申请，并可实现上述证件真伪验证方法。本申请实施例所称的程序模块是指能够完成特定功能的一系列计算机程序指令段，比程序本身更适合于描述证件真伪验证***20在存储介质中的执行过程。以下描述将具体介绍本申请实施例各程序模块的功能：Please continue to refer to FIG. 9, which shows a schematic diagram of program modules of the certificate authenticity verification system of the present application. In the embodiment of the present application, the certificate authenticity verification system 20 may include or be divided into one or more program modules, one or more program modules are stored in a storage medium and executed by one or more processors, In order to complete this application, the above-mentioned certificate authenticity verification method can be realized. The program module referred to in the embodiments of the present application refers to a series of computer program instruction segments capable of completing specific functions, and is more suitable for describing the execution process of the certificate authenticity verification system 20 in the storage medium than the program itself. The following description will specifically introduce the functions of each program module in the embodiments of the present application:

获取模块200，用于获取原始证件图像，识别所述原始证件图像的证件类型.Acquisition module 200, for acquiring the original document image, identifying the document type of the original document image.

处理模块210，用于基于所述证件类型，从所述原始证件图像中提取多个特征信息，并对所述多个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果。The processing module 210 is configured to extract multiple characteristic information from the original document image based on the document type, and analyze the multiple characteristic information to obtain multiple target characteristic information. The characteristic information is verified to generate multiple verification results.

结果生成模块220，用于根据所述文字校验结果及多个图像校验结果，以生成验真结论表单。The result generation module 220 is configured to generate a verification conclusion form according to the text verification result and multiple image verification results.

实施例三Example three

参阅图10，是本申请实施例三之计算机设备的硬件架构示意图。本申请实施例中，所述计算机设备2是一种能够按照事先设定或者存储的指令，自动进行数值计算和/或信息处理的设备。该计算机设备2可以是机架式服务器、刀片式服务器、塔式服务器或机柜式服务器(包括独立的服务器，或者多个服务器所组成的服务器集群)等。如图10所示，所述计算机设备2至少包括，但不限于，可通过***总线相互通信连接存储器21、处理器22、网络接口23、以及证件真伪验证***20。其中：Refer to FIG. 10, which is a schematic diagram of the hardware architecture of the computer device according to the third embodiment of the present application. In the embodiment of the present application, the computer device 2 is a device that can automatically perform numerical calculation and/or information processing according to pre-set or stored instructions. The computer device 2 may be a rack server, a blade server, a tower server, or a cabinet server (including an independent server or a server cluster composed of multiple servers). As shown in FIG. 10, the computer device 2 at least includes, but is not limited to, a memory 21, a processor 22, a network interface 23, and a certificate authenticity verification system 20 that can communicate with each other through a system bus. among them:

本申请实施例中，存储器21至少包括一种类型的非易失性计算机可读存储介质，所述非易失性计算机可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、 光盘等。在一些实施例中，存储器21可以是计算机设备2的内部存储单元，例如该计算机设备2的硬盘或内存。在另一些实施例中，存储器21也可以是计算机设备2的外部存储设备，例如该计算机设备2上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。当然，存储器21还可以既包括计算机设备2的内部存储单元也包括其外部存储设备。本申请实施例中，存储器21通常用于存储安装于计算机设备2的操作***和各类应用软件，例如实施例二的证件真伪验证***20的程序代码等。此外，存储器21还可以用于暂时地存储已经输出或者将要输出的各类数据。In the embodiment of the present application, the memory 21 includes at least one type of non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD Or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), Magnetic storage, magnetic disks, optical discs, etc. In some embodiments, the memory 21 may be an internal storage unit of the computer device 2, for example, a hard disk or a memory of the computer device 2. In other embodiments, the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a smart media card (SMC), and a secure digital (Secure Digital, SMC) equipped on the computer device 2. SD) card, flash card (Flash Card), etc. Of course, the memory 21 may also include both the internal storage unit of the computer device 2 and its external storage device. In the embodiment of the present application, the memory 21 is generally used to store the operating system and various application software installed in the computer device 2, for example, the program code of the certificate authenticity verification system 20 in the second embodiment. In addition, the memory 21 can also be used to temporarily store various types of data that have been output or will be output.

处理器22在一些实施例中可以是中央处理器(Central Processing Unit，CPU)、控制器、微控制器、微处理器、或其他数据处理芯片。该处理器22通常用于控制计算机设备2的总体操作。本申请实施例中，处理器22用于运行存储器21中存储的程序代码或者处理数据，例如运行证件真伪验证***20，以实现实施例一的证件真伪验证方法。The processor 22 may be a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 22 is generally used to control the overall operation of the computer device 2. In the embodiment of the present application, the processor 22 is used to run the program code or process data stored in the memory 21, for example, to run the certificate authenticity verification system 20 to implement the certificate authenticity verification method of the first embodiment.

所述网络接口23可包括无线网络接口或有线网络接口，该网络接口23通常用于在所述计算机设备2与其他电子装置之间建立通信连接。例如，所述网络接口23用于通过网络将所述计算机设备2与外部终端相连，在所述计算机设备2与外部终端之间的建立数据传输通道和通信连接等。所述网络可以是企业内部网(Intranet)、互联网(Internet)、全球移动通讯***(Global System of Mobile communication，GSM)、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)、4G网络、5G网络、蓝牙(Bluetooth)、Wi-Fi等无线或有线网络。The network interface 23 may include a wireless network interface or a wired network interface, and the network interface 23 is generally used to establish a communication connection between the computer device 2 and other electronic devices. For example, the network interface 23 is used to connect the computer device 2 with an external terminal through a network, and establish a data transmission channel and a communication connection between the computer device 2 and the external terminal. The network may be Intranet, Internet, Global System of Mobile Communication (GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G Network, Bluetooth (Bluetooth), Wi-Fi and other wireless or wired networks.

需要指出的是，图10仅示出了具有部件20-23的计算机设备2，但是应理解的是，并不要求实施所有示出的部件，可以替代的实施更多或者更少的部件。It should be pointed out that FIG. 10 only shows the computer device 2 with components 20-23, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

在本申请实施例中，存储于存储器21中的所述证件真伪验证***20还可以被分割为一个或者多个程序模块，所述一个或者多个程序模块被存储于存储器21中，并由一个或多个处理器(本申请实施例为处理器22)所执行，以完成本申请。In the embodiment of the present application, the certificate authenticity verification system 20 stored in the memory 21 may also be divided into one or more program modules, and the one or more program modules are stored in the memory 21 and are One or more processors (the embodiment of the present application is the processor 22) are executed to complete the present application.

例如，图9示出了所述实现证件真伪验证***20实施例二的程序模块示意图，该实施例中，所述基于证件真伪验证***20可以被划分为获取模块200、处理模块210、结果生成模块220。其中，本申请所称的程序模块是指能够完成特定功能的一系列计算机程序指令段所述程序模块200-220的具体功能在实施例二中已有详细描述，在此不再赘述。For example, FIG. 9 shows a schematic diagram of program modules for implementing the second embodiment of the certificate authenticity verification system 20. In this embodiment, the certificate authenticity verification system 20 can be divided into an acquisition module 200, a processing module 210, The result generation module 220. Wherein, the program module referred to in the present application refers to a series of computer program instruction segments capable of completing specific functions. The specific functions of the program modules 200-220 have been described in detail in the second embodiment, and will not be repeated here.

实施例四Example four

本申请实施例还提供一种非易失性计算机可读存储介质，如闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘、服务器、App应用商城等等，其上存储有计算机可读指令，程序 被处理器执行时实现相应功能。本申请实施例的非易失性计算机可读存储介质用于存储证件真伪验证***20，被处理器执行时实现实施例一的证件真伪验证方法。The embodiments of the present application also provide a non-volatile computer-readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, server, App application mall, etc., on which Stored with computer-readable instructions, the program implements corresponding functions when executed by the processor. The non-volatile computer-readable storage medium of the embodiment of the present application is used to store the certificate authenticity verification system 20, and when executed by a processor, realizes the certificate authenticity verification method of the first embodiment.

上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。The serial numbers of the foregoing embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。Through the description of the above implementation manners, those skilled in the art can clearly understand that the above-mentioned embodiment method can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is better.的实施方式。

以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。The above are only the preferred embodiments of the application, and do not limit the scope of the patent for this application. Any equivalent structure or equivalent process transformation made using the content of the description and drawings of the application, or directly or indirectly applied to other related technical fields , The same reason is included in the scope of patent protection of this application.

Claims (20)

1. 一种证件真伪验证方法，包括：A method for verifying the authenticity of a certificate, including:

   获取原始证件图像，识别所述原始证件图像的证件类型；Obtain the original certificate image, and identify the certificate type of the original certificate image;

   基于所述证件类型，从所述原始证件图像中提取多个特征信息，并对所述多个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果；Based on the document type, extract multiple feature information from the original document image, and analyze the multiple feature information to obtain multiple target feature information, and verify the multiple target feature information, To generate multiple verification results;

   根据所述多个校验结果，以生成验真结论表单。According to the multiple verification results, a verification conclusion form is generated.
2. 根据权利要求1所述的证件真伪验证方法，所述多个特征信息包括多个特征向量序列及多个图像区域；The method for verifying the authenticity of a document according to claim 1, wherein the plurality of characteristic information includes a plurality of characteristic vector sequences and a plurality of image regions;

   所述基于所述证件类型，从所述原始证件图像中提取多个特征信息，并对所述多个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果的步骤，包括：Said extracting a plurality of characteristic information from the original document image based on the certificate type, and analyzing the plurality of characteristic information to obtain a plurality of target characteristic information, and collating the plurality of target characteristic information To generate multiple verification results, including:

   对所述原始证件图像进行定位，以获取多个特征向量序列及所述多个特征向量序列对应的多个位置标识；Positioning the original document image to obtain multiple feature vector sequences and multiple location identifiers corresponding to the multiple feature vector sequences;

   从所述多个特征向量序列中提取多个文字特征向量序列；Extracting multiple text feature vector sequences from the multiple feature vector sequences;

   基于所述证件类型，对所述多个文字特征向量序列进行识别操作，以获取所述多个文字特征向量序列对应的多个目标文字；Performing a recognition operation on the multiple character feature vector sequences based on the certificate type to obtain multiple target characters corresponding to the multiple character feature vector sequences;

   基于所述证件类型及多个位置标识，获取与所述证件类型对应的多个预设的文字内容规则；Based on the certificate type and multiple location identifiers, obtaining a plurality of preset text content rules corresponding to the certificate type;

   基于所述证件类型及多个所述文字内容规则，对所述多个目标文字进行校验，以生成文字校验结果。Based on the certificate type and the multiple text content rules, the multiple target texts are verified to generate text verification results.
3. 根据权利要求2所述的证件真伪验证方法，所述对所述原始证件图像进行定位，以获取多个特征向量序列及所述多个特征向量序列对应的多个位置标识包括：The method for verifying the authenticity of a document according to claim 2, wherein the positioning the original document image to obtain multiple feature vector sequences and multiple location identifiers corresponding to the multiple feature vector sequences comprises:

   对所述原始证件图像进行卷积，得到多个卷积特征图；Convolve the original document image to obtain multiple convolution feature maps;

   对多个卷积特征图进行池化，得到多个降维后的卷积特征图；Pooling multiple convolution feature maps to obtain multiple dimensionality reduction convolution feature maps;

   将多个降维后的卷积特征图中的多个卷积特征转化为多个特征向量序列；Convert multiple convolution features in multiple reduced dimensionality convolution feature maps into multiple feature vector sequences;

   获取多个特征向量序列对应的位置坐标关系，并基于所述位置坐标关系以及预设规则，得到多个特征向量序列对应的多个位置标识。The position coordinate relationship corresponding to the multiple feature vector sequences is acquired, and based on the position coordinate relationship and the preset rule, multiple location identifiers corresponding to the multiple feature vector sequences are obtained.
4. 根据权利要求2所述的证件真伪验证方法，所述原始证件图像包括证件正面拍摄图像和至少两个证件侧面拍摄图像；The method for verifying the authenticity of a certificate according to claim 2, wherein the original certificate image includes a front-side photographed image of the certificate and at least two side-side photographed images of the certificate;

   所述基于所述证件类型，从所述原始证件图像中提取多个特征信息，并对所述多个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果的步骤，包括：Said extracting a plurality of characteristic information from the original document image based on the certificate type, and analyzing the plurality of characteristic information to obtain a plurality of target characteristic information, and collating the plurality of target characteristic information To generate multiple verification results, including:

   根据预设的防伪标签从所述证件正面拍摄图像提取持证人照片人像区域及标准人像区域；Extracting a portrait area and a standard portrait area of the holder's photo from the image taken on the front of the document according to the preset anti-counterfeiting label;

   将所述持证人照片人像区域与标准人像区域进行匹配，以获取人脸校验结果；当持证人照片人像区域与标准人像区域匹配一致时，则判定所述人脸校验结果为校验成功；当持证人照片人像区域与标准人像区域匹配不一致时，则判定人脸校验结果为校验失败。Match the portrait area of the holder’s photo with the standard portrait area to obtain the face verification result; when the portrait area of the holder’s photo matches the standard portrait area, it is determined that the face verification result is a calibration result. The verification is successful; when the portrait area of the holder's photo is inconsistent with the standard portrait area, the face verification result is determined to be a verification failure.
5. 根据权利要求4所述的证件真伪验证方法，所述基于所述证件类型，从所述原始证件图像中提取多个特征信息，并对所述多个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果的步骤，还包括：The method for verifying the authenticity of a document according to claim 4, wherein based on the document type, a plurality of characteristic information is extracted from the original document image, and the plurality of characteristic information is analyzed to obtain a plurality of targets The feature information, the step of verifying the multiple target feature information to generate multiple verification results, further includes:

   根据预设的防伪标签从所述证件正面拍摄图像中提取目标彩虹印刷区域；Extracting the target rainbow printing area from the photographed image on the front of the document according to the preset anti-counterfeiting label;

   获取目标彩虹印刷区域的整体颜色渐变风格与标准证件的整体颜色渐变风格的第一相似度；Obtain the first similarity between the overall color gradient style of the target rainbow printing area and the overall color gradient style of the standard certificate;

   将所述第一相似度与预设的第一阈值进行对比，以获取整体颜色渐变风格校验结果：当所述第一相似度高于所述第一阈值时，则判定整体颜色渐变风格校验结果为校验成功；当所述第一相似度低于所述第一阈值时，则判定整体颜色渐变风格校验结果为校验失败。The first similarity is compared with a preset first threshold to obtain the overall color gradient style verification result: when the first similarity is higher than the first threshold, the overall color gradient style correction is determined The verification result is that the verification is successful; when the first similarity is lower than the first threshold, it is determined that the verification result of the overall color gradient style is a verification failure.
6. 根据权利要求5所述的证件真伪验证方法，所述基于所述证件类型，从所述原始证件图像中提取多个特征信息，并对所述多个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果的步骤，还包括：The method for verifying the authenticity of a document according to claim 5, wherein based on the document type, a plurality of characteristic information is extracted from the original document image, and the plurality of characteristic information is analyzed to obtain a plurality of targets The feature information, the step of verifying the multiple target feature information to generate multiple verification results, further includes:

   根据预设的防伪标签从至少两个所述证件侧面拍摄图像中提取目标多元化图案背景区域；Extracting a target diversified pattern background area from at least two images taken from the side of the document according to a preset anti-counterfeiting label;

   获取目标多元化图案背景区域与标准证件的多元化图案背景区域的第二相似度；Obtain the second degree of similarity between the target diversified pattern background area and the diversified pattern background area of the standard certificate;

   将所述第二相似度与预设的第二阈值进行对比，以获取多元化图案背景校验结果：当所述第二相似度高于所述第二阈值，则判定多元化图案背景校验结果为校验成功；当所述第二相似度低于所述第二阈值，则判定多元化图案背景校验结果为校验失败。The second similarity degree is compared with a preset second threshold value to obtain a multiple pattern background check result: when the second similarity degree is higher than the second threshold value, a multiple pattern background check result is determined The result is that the verification is successful; when the second degree of similarity is lower than the second threshold, it is determined that the verification result of the background of the plural patterns is a verification failure.
7. 根据权利要求6所述的证件真伪验证方法，所述基于所述证件类型，从所述原始证件图像中提取多个特征信息，并对所述多个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果的步骤，还包括：The method for verifying the authenticity of a document according to claim 6, wherein based on the document type, a plurality of characteristic information is extracted from the original document image, and the plurality of characteristic information is analyzed to obtain a plurality of targets The feature information, the step of verifying the multiple target feature information to generate multiple verification results, further includes:

   根据预设的防伪标签从至少两个所述证件侧面拍摄图像中提取多个目标光学变色油墨三角形区域与多个目标具波浪及立体效果的全息图区域；Extracting a plurality of target optically color-changing ink triangle regions and a plurality of target hologram regions with wave and three-dimensional effects from at least two images taken from the side of the document according to a preset anti-counterfeiting label;

   获取目标光学变色油墨三角形区域与标准证件的光学变色油墨三角形区域的第三相似度以及目标具波浪及立体效果的全息图区域与标准证件的具波浪及立体效果的全息图区域的第四相似度；Obtain the third degree of similarity between the triangular area of the target optical color-changing ink and the triangular area of the optical color-changing ink of the standard document, and the fourth degree of similarity between the hologram area of the target with wave and three-dimensional effect and the hologram area of the standard document with wave and three-dimensional effect ；

   将所述第三相似度与预设的第三阈值进行对比，将所述第四相似度与预设的第四阈值进行对比，以获取背景图案校验结果：当第三相似度高于所述第三阈值，且所述第四相似度高于所述第四阈值；则判定背景图案校验结果为校验成功；当第三相似度低于所述第三阈值 和/或所述第四相似度低于所述第四阈值；则判定背景图案校验结果为校验失败。The third similarity is compared with the preset third threshold, and the fourth similarity is compared with the preset fourth threshold to obtain the background pattern verification result: when the third similarity is higher than all The third threshold, and the fourth similarity is higher than the fourth threshold; then it is determined that the background pattern verification result is a successful verification; when the third similarity is lower than the third threshold and/or the first The four similarities are lower than the fourth threshold; then it is determined that the background pattern verification result is a verification failure.
8. 根据权利要求7所述的证件真伪验证方法，所述基于所述证件类型，从所述原始证件图像中提取多个特征信息，并对所述多个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果的步骤，还包括：The method for verifying the authenticity of a document according to claim 7, wherein based on the document type, a plurality of characteristic information is extracted from the original document image, and the plurality of characteristic information is analyzed to obtain a plurality of targets The feature information, the step of verifying the multiple target feature information to generate multiple verification results, further includes:

   根据预设的防伪标签从所述证件正面拍摄图像中提取目标微缩文字印刷区域及目标透明窗区域，所述目标透明窗区域包括用户个人资料；Extracting a target microtext printing area and a target transparent window area from a photographed image on the front of the document according to a preset anti-counterfeiting label, where the target transparent window area includes the user's personal data;

   将所述目标微缩文字印刷区域进行放大操作，以得到放大后的目标微缩文字印刷区域；Performing an enlargement operation on the target microtext printing area to obtain an enlarged target microtext printing area;

   获取目标微缩文字印刷区域与标准证件的微缩文字印刷区域的第五相似度以及目标透明窗区域与所述证件类型对应的数据库中对应的用户个人资料的第六相似度；Acquiring the fifth similarity between the target microtext printing area and the microtext printing area of the standard certificate and the sixth similarity between the target transparent window area and the corresponding user profile in the database corresponding to the certificate type;

   将所述第五相似度与预设的第五阈值进行比对，将所述第六相似度与预设的第六阈值进行比对，以获取内容校验结果：当所述第五相似度高于所述第五阈值，且所述第六相似度高于所述第六阈值时，则判定内容校验结果为校验成功；当第五相似度低于所述第五阈值和/或所述第六相似度低于所述第六阈值，则判定内容校验结果为校验失败。The fifth similarity degree is compared with a preset fifth threshold, and the sixth similarity degree is compared with a preset sixth threshold value to obtain a content verification result: when the fifth similarity degree When it is higher than the fifth threshold and the sixth similarity is higher than the sixth threshold, it is determined that the content verification result is a successful verification; when the fifth similarity is lower than the fifth threshold and/or If the sixth similarity is lower than the sixth threshold, it is determined that the content verification result is a verification failure.
9. 一种证件真伪验证***，包括：A certificate authenticity verification system, including:

   获取模块，用于获取原始证件图像，识别所述原始证件图像的证件类型；The acquisition module is used to acquire the original certificate image and identify the certificate type of the original certificate image;

   处理模块，基于所述证件类型，从所述原始证件图像中提取多个特征信息，并对所述多个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果；The processing module, based on the document type, extracts multiple feature information from the original document image, and analyzes the multiple feature information to obtain multiple target feature information, and perform processing on the multiple target feature information Check to generate multiple check results;

   结果生成模块，用于根据所述多个校验结果，以生成验真结论表单。The result generation module is used to generate a verification conclusion form according to the multiple verification results.
10. 根据权利要求9所述的证件真伪验证***，所述多个特征信息包括多个特征向量序列及多个图像区域；The certificate authenticity verification system according to claim 9, wherein the plurality of characteristic information includes a plurality of characteristic vector sequences and a plurality of image regions;

    所述处理模块包括：第一获取模块，用于对所述原始证件图像进行定位，以获取多个特征向量序列及所述多个特征向量序列对应的多个位置标识；The processing module includes: a first acquisition module, configured to locate the original document image to acquire multiple feature vector sequences and multiple location identifiers corresponding to the multiple feature vector sequences;

    第一提取模块，用于从所述多个特征向量序列中提取多个文字特征向量序列；The first extraction module is configured to extract multiple character feature vector sequences from the multiple feature vector sequences;

    第一识别模块，用于基于所述证件类型，对所述多个文字特征向量序列进行识别操作，以获取所述多个文字特征向量序列对应的多个目标文字；The first recognition module is configured to perform a recognition operation on the multiple character feature vector sequences based on the certificate type to obtain multiple target characters corresponding to the multiple character feature vector sequences;

    第二获取模块，用于基于所述证件类型及多个位置标识，获取与所述证件类型对应的多个预设的文字内容规则；The second obtaining module is configured to obtain a plurality of preset text content rules corresponding to the certificate type based on the certificate type and multiple location identifiers;

    第一校验模块，用于基于所述证件类型及多个所述文字内容规则，对所述多个目标文字进行校验，以生成文字校验结果。The first verification module is configured to verify the multiple target texts based on the certificate type and the multiple text content rules to generate a text verification result.
11. 根据权利要求10所述的证件真伪验证***，所述原始证件图像包括证件正面拍摄图像和至少两个证件侧面拍摄图像；The certificate authenticity verification system according to claim 10, wherein the original certificate image comprises a front-side photographed image of the certificate and at least two side-side photographed images of the certificate;

    所述处理模块包括：第二提取模块，用于根据预设的防伪标签从所述证件正面拍摄图像提取持证人照片人像区域及标准人像区域；The processing module includes: a second extraction module for extracting a portrait area and a standard portrait area of the holder's photo from the image taken on the front of the document according to a preset anti-counterfeiting label;

    第二校验模块，用于将所述持证人照片人像区域与标准人像区域进行匹配，以获取人脸校验结果；当持证人照片人像区域与标准人像区域匹配一致时，则判定所述人脸校验结果为校验成功；当持证人照片人像区域与标准人像区域匹配不一致时，则判定人脸校验结果为校验失败。The second verification module is used to match the portrait area of the holder’s photo with the standard portrait area to obtain the face verification result; when the portrait area of the holder’s photo matches the standard portrait area, it is determined that all The face verification result is a successful verification; when the portrait area of the holder's photo is inconsistent with the standard portrait area, the face verification result is determined to be a verification failure.
12. 根据权利要求11所述的证件真伪验证***，所述处理模块包括：第三提取模块，用于根据预设的防伪标签从所述证件正面拍摄图像中提取目标彩虹印刷区域；The certificate authenticity verification system according to claim 11, wherein the processing module comprises: a third extraction module, configured to extract a target rainbow printing area from a photographed image on the front of the certificate according to a preset anti-counterfeiting label;

    第三获取模块，用于获取目标彩虹印刷区域的整体颜色渐变风格与标准证件的整体颜色渐变风格的第一相似度；The third acquisition module is used to acquire the first similarity between the overall color gradient style of the target rainbow printing area and the overall color gradient style of the standard certificate;

    第三校验模块，用于将所述第一相似度与预设的第一阈值进行对比，以获取整体颜色渐变风格校验结果：当所述第一相似度高于所述第一阈值时，则判定整体颜色渐变风格校验结果为校验成功；当所述第一相似度低于所述第一阈值时，则判定整体颜色渐变风格校验结果为校验失败。The third verification module is configured to compare the first similarity with a preset first threshold to obtain an overall color gradient style verification result: when the first similarity is higher than the first threshold , It is determined that the overall color gradient style verification result is a successful verification; when the first similarity is lower than the first threshold, it is determined that the overall color gradient style verification result is a verification failure.
13. 根据权利要求12所述的证件真伪验证***，所述处理模块包括：第四提取模块，用于根据预设的防伪标签从至少两个所述证件侧面拍摄图像中提取目标多元化图案背景区域；The document authenticity verification system according to claim 12, wherein the processing module comprises: a fourth extraction module for extracting a target diversified pattern background area from at least two images taken from the side of the document according to a preset anti-counterfeiting label ；

    第四获取模块，用于获取目标多元化图案背景区域与标准证件的多元化图案背景区域的第二相似度；The fourth obtaining module is used to obtain the second degree of similarity between the target diversified pattern background area and the diversified pattern background area of the standard certificate;

    第四校验模块，用于将所述第二相似度与预设的第二阈值进行对比，以获取多元化图案背景校验结果：当所述第二相似度高于所述第二阈值，则判定多元化图案背景校验结果为校验成功；当所述第二相似度低于所述第二阈值，则判定多元化图案背景校验结果为校验失败。The fourth verification module is configured to compare the second similarity with a preset second threshold to obtain a multi-pattern background verification result: when the second similarity is higher than the second threshold, Then, it is determined that the multi-pattern background verification result is a successful verification; when the second similarity is lower than the second threshold, the multi-pattern background verification result is determined to be a verification failure.
14. 根据权利要求13所述的证件真伪验证***，所述处理模块包括：第五提取模块，用于根据预设的防伪标签从至少两个所述证件侧面拍摄图像中提取多个目标光学变色油墨三角形区域与多个目标具波浪及立体效果的全息图区域；The certificate authenticity verification system according to claim 13, wherein the processing module comprises: a fifth extraction module, configured to extract a plurality of target optical color-changing inks from at least two images taken from the side of the certificate according to a preset anti-counterfeiting label Triangular area and multiple target hologram areas with wave and three-dimensional effects;

    第五获取模块，用于获取目标光学变色油墨三角形区域与标准证件的光学变色油墨三角形区域的第三相似度以及目标具波浪及立体效果的全息图区域与标准证件的具波浪及立体效果的全息图区域的第四相似度；The fifth acquisition module is used to acquire the third similarity between the triangular area of the target optical color-changing ink and the triangular area of the optical color-changing ink of the standard document, and the hologram area of the target with wave and three-dimensional effect and the hologram with wave and three-dimensional effect of the standard document The fourth similarity of the graph area;

    第五校验模块，用于将所述第三相似度与预设的第三阈值进行对比，将所述第四相似度与预设的第四阈值进行对比，以获取背景图案校验结果：当第三相似度高于所述第三阈值，且所述第四相似度高于所述第四阈值；则判定背景图案校验结果为校验成功；当第三相似度低于所述第三阈值和/或所述第四相似度低于所述第四阈值；则判定背景图案校验结果为校验失败。The fifth verification module is configured to compare the third similarity with a preset third threshold, and compare the fourth similarity with a preset fourth threshold to obtain a background pattern verification result: When the third similarity is higher than the third threshold, and the fourth similarity is higher than the fourth threshold; it is determined that the background pattern verification result is a successful verification; when the third similarity is lower than the first The three thresholds and/or the fourth similarity is lower than the fourth threshold; then it is determined that the background pattern verification result is a verification failure.
15. 根据权利要求14所述的证件真伪验证***，所述处理模块包括：第六提取模块，用于根据预设的防伪标签从所述证件正面拍摄图像中提取目标微缩文字印刷区域及目标透 明窗区域，所述目标透明窗区域包括用户个人资料；The certificate authenticity verification system according to claim 14, wherein the processing module comprises: a sixth extraction module for extracting the target microtext printing area and the target transparent window from the image taken on the front of the certificate according to a preset anti-counterfeiting label Area, the target transparent window area includes user personal data;

    放大模块，用于将所述目标微缩文字印刷区域进行放大操作，以得到放大后的目标微缩文字印刷区域；An enlargement module, used to perform an enlargement operation on the target micro-text printing area to obtain an enlarged target micro-text printing area;

    第六获取模块，用于获取目标微缩文字印刷区域与标准证件的微缩文字印刷区域的第五相似度以及目标透明窗区域与所述证件类型对应的数据库中对应的用户个人资料的第六相似度；The sixth obtaining module is used to obtain the fifth similarity between the target micro-text printing area and the micro-text printing area of the standard certificate and the sixth similarity between the target transparent window area and the corresponding user profile in the database corresponding to the certificate type ；

    第六校验模块，用于将所述第五相似度与预设的第五阈值进行比对，将所述第六相似度与预设的第六阈值进行比对，以获取内容校验结果：当所述第五相似度高于所述第五阈值，且所述第六相似度高于所述第六阈值时，则判定内容校验结果为校验成功；当第五相似度低于所述第五阈值和/或所述第六相似度低于所述第六阈值，则判定内容校验结果为校验失败。The sixth verification module is configured to compare the fifth similarity with a preset fifth threshold, and compare the sixth similarity with a preset sixth threshold to obtain a content verification result : When the fifth similarity is higher than the fifth threshold, and the sixth similarity is higher than the sixth threshold, it is determined that the content verification result is a successful verification; when the fifth similarity is lower than If the fifth threshold and/or the sixth similarity are lower than the sixth threshold, it is determined that the content verification result is a verification failure.
16. 一种计算机设备，所述计算机设备包括存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的计算机可读指令，所述处理器执行所述计算机可读指令时执行以下步骤：A computer device that includes a memory, a processor, and computer-readable instructions stored on the memory and capable of running on the processor. The processor executes the following when executing the computer-readable instructions step:

    获取原始证件图像，识别所述原始证件图像的证件类型；Obtain the original certificate image, and identify the certificate type of the original certificate image;

    基于所述证件类型，从所述原始证件图像中提取多个特征信息，并对所述多个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果；Based on the document type, extract multiple feature information from the original document image, and analyze the multiple feature information to obtain multiple target feature information, and verify the multiple target feature information, To generate multiple verification results;

    根据所述多个校验结果，以生成验真结论表单。According to the multiple verification results, a verification conclusion form is generated.
17. 根据权利要求16所述的计算机设备，所述多个特征信息包括多个特征向量序列及多个图像区域；所述处理器执行所述计算机可读指令时执行以下步骤：The computer device according to claim 16, wherein the plurality of feature information includes a plurality of feature vector sequences and a plurality of image regions; when the processor executes the computer readable instruction, the following steps are performed:

    对所述原始证件图像进行定位，以获取多个特征向量序列及所述多个特征向量序列对应的多个位置标识；Positioning the original document image to obtain multiple feature vector sequences and multiple location identifiers corresponding to the multiple feature vector sequences;

    从所述多个特征向量序列中提取多个文字特征向量序列；Extracting multiple text feature vector sequences from the multiple feature vector sequences;

    基于所述证件类型，对所述多个文字特征向量序列进行识别操作，以获取所述多个文字特征向量序列对应的多个目标文字；Performing a recognition operation on the multiple character feature vector sequences based on the certificate type to obtain multiple target characters corresponding to the multiple character feature vector sequences;

    基于所述证件类型及多个位置标识，获取与所述证件类型对应的多个预设的文字内容规则；Based on the certificate type and multiple location identifiers, obtaining a plurality of preset text content rules corresponding to the certificate type;

    基于所述证件类型及多个所述文字内容规则，对所述多个目标文字进行校验，以生成文字校验结果。Based on the certificate type and the multiple text content rules, the multiple target texts are verified to generate text verification results.
18. 根据权利要求17所述的计算机设备，所述原始证件图像包括证件正面拍摄图像和至少两个证件侧面拍摄图像；所述处理器执行所述计算机可读指令时执行以下步骤：The computer device according to claim 17, wherein the original document image comprises a front-side photographed image of the certificate and at least two side-side photographed images of the certificate; the processor executes the following steps when executing the computer-readable instructions:

    根据预设的防伪标签从所述证件正面拍摄图像提取持证人照片人像区域及标准人像区域；Extracting a portrait area and a standard portrait area of the holder's photo from the image taken on the front of the document according to the preset anti-counterfeiting label;

    将所述持证人照片人像区域与标准人像区域进行匹配，以获取人脸校验结果；当持证 人照片人像区域与标准人像区域匹配一致时，则判定所述人脸校验结果为校验成功；当持证人照片人像区域与标准人像区域匹配不一致时，则判定人脸校验结果为校验失败。Match the portrait area of the holder’s photo with the standard portrait area to obtain the face verification result; when the portrait area of the holder’s photo matches the standard portrait area, it is determined that the face verification result is a calibration result. The verification is successful; when the portrait area of the holder's photo is inconsistent with the standard portrait area, the face verification result is determined to be a verification failure.
19. 根据权利要求18所述的计算机设备，所述处理器执行所述计算机可读指令时执行以下步骤：The computer device according to claim 18, wherein the processor executes the following steps when executing the computer readable instruction:

    根据预设的防伪标签从所述证件正面拍摄图像中提取目标彩虹印刷区域；Extracting the target rainbow printing area from the photographed image on the front of the document according to the preset anti-counterfeiting label;

    获取目标彩虹印刷区域的整体颜色渐变风格与标准证件的整体颜色渐变风格的第一相似度；Obtain the first similarity between the overall color gradient style of the target rainbow printing area and the overall color gradient style of the standard certificate;

    将所述第一相似度与预设的第一阈值进行对比，以获取整体颜色渐变风格校验结果：当所述第一相似度高于所述第一阈值时，则判定整体颜色渐变风格校验结果为校验成功；当所述第一相似度低于所述第一阈值时，则判定整体颜色渐变风格校验结果为校验失败。The first similarity is compared with a preset first threshold to obtain the overall color gradient style verification result: when the first similarity is higher than the first threshold, the overall color gradient style correction is determined The verification result is that the verification is successful; when the first similarity is lower than the first threshold, it is determined that the verification result of the overall color gradient style is a verification failure.
20. 一种非易失性计算机可读存储介质，所述非易失性计算机可读存储介质内存储有计算机可读指令，所述计算机可读指令可被至少一个处理器所执行，以使所述至少一个处理器执行以下步骤：A non-volatile computer-readable storage medium having computer-readable instructions stored in the non-volatile computer-readable storage medium, and the computer-readable instructions can be executed by at least one processor to cause the At least one processor performs the following steps:

    获取原始证件图像，识别所述原始证件图像的证件类型；Obtain the original certificate image, and identify the certificate type of the original certificate image;

    基于所述证件类型，从所述原始证件图像中提取多个特征信息，并对所述多个特征信息进行解析，以得到多个目标特征信息，对所述多个目标特征信息进行校验，以生成多个校验结果；Based on the document type, extract multiple feature information from the original document image, and analyze the multiple feature information to obtain multiple target feature information, and verify the multiple target feature information, To generate multiple verification results;

    根据所述多个校验结果，以生成验真结论表单。According to the multiple verification results, a verification conclusion form is generated.

Images