CN111858500A - Electronic image naming method, device, equipment and readable storage medium - Google Patents
Electronic image naming method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN111858500A CN111858500A CN202010777838.7A CN202010777838A CN111858500A CN 111858500 A CN111858500 A CN 111858500A CN 202010777838 A CN202010777838 A CN 202010777838A CN 111858500 A CN111858500 A CN 111858500A
- Authority
- CN
- China
- Prior art keywords
- name
- electronic image
- image
- sequence
- electronic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
- G06F16/164—File meta data generation
- G06F16/166—File name conversion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application provides a method, a device and equipment for naming electronic images and a readable storage medium, wherein a first name is obtained and is the name of a first electronic image, and if the first name is consistent with the name of an associated attachment of a second electronic image, the name of the first electronic image is modified from the first name to the name of the second electronic image, wherein the first electronic image and the second electronic image belong to the same image sequence, and the second electronic image is an adjacent image sequenced before the first electronic image. Therefore, compared with the manual naming and sequencing method in the prior art, the method automatically acquires the name of each electronic image in the image sequence, modifies the name of the electronic image according to the incidence relation between adjacent electronic images, improves the naming efficiency, and enables the naming of the image to more accurately accord with the preset rule.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a method, an apparatus, a device, and a readable storage medium for naming an electronic image.
Background
After scanning or photographing and digitizing the entity files of the document class, the obtained electronic images are often required to be filed respectively according to folders, and then the images belonging to the same folder are sorted and renamed according to a specific industry rule. In a traditional processing mode, a processing person opens the same batch of images in batch in image naming software, and then names each image in sequence.
It can be seen that the method of using manual sorting nomenclature is susceptible to the ability or physical condition of the processing personnel, resulting in low efficiency and accuracy.
Disclosure of Invention
In view of the above, the present application provides a method, an apparatus, a device and a readable storage medium for naming an electronic image, which are used to improve efficiency and accuracy of naming an electronic image, as follows:
a method for naming an electronic image, comprising:
obtaining a first name, the first name being a name of a first electronic image;
and if the first name is consistent with the name of the associated attachment of the second electronic image, modifying the name of the first electronic image from the first name into the name of the second electronic image, wherein the first electronic image and the second electronic image belong to the same image sequence, and the second electronic image is an adjacent image sequenced before the first electronic image.
Optionally, the method further comprises:
if the order of the names in the name sequence is different from the preset ordering rule, sending a modification prompt;
the name sequence is the name of an electronic image in the image sequence, the sequence is formed by arranging the names according to the sequence of the electronic images, and the sequencing rule is determined according to the type of the electronic image in the image sequence.
Optionally, the ordering rule comprises:
the method comprises the steps of obtaining the corresponding relation of an index number, a category number, a name and the category number of an associated accessory, wherein the index number is used for indicating the sequence of the name.
Optionally, the first name is identical to a name of an associated attachment to the second electronic image, including:
the category number of the first name is the same as the category number of the associated attachment corresponding to the name of the second electronic image.
Optionally, the method further comprises:
and if the sequence of the names in the name sequence is the same as the preset sequencing rule, storing the electronic image according to the name of the electronic image.
Optionally, obtaining the first name includes:
inputting the first electronic image into a preset classification model to obtain a name to be selected of the first electronic image output by the classification model;
the classification model is used for selecting the name to be selected of the first electronic image and the confidence coefficient of the selected name from a plurality of preset names according to the characteristics of the first electronic image;
and taking the name to be selected with the confidence coefficient not less than a preset threshold value as the first name.
Optionally, the method further comprises:
if the confidence coefficient of the name to be selected is smaller than the preset threshold value, character recognition is carried out on the preset area of the first electronic image, and recognition content is obtained;
and taking the preset name matched with the identification content as the first name.
An electronic image naming apparatus comprising:
a name acquisition unit configured to acquire a first name that is a name of a first electronic image;
and the name modifying unit is used for modifying the name of the first electronic image into the name of the second electronic image from the first name if the first name is consistent with the name of the associated attachment of the second electronic image, wherein the first electronic image and the second electronic image belong to the same image sequence, and the second electronic image is an adjacent image sequenced before the first electronic image.
A naming device for electronic images, comprising: a memory and a processor;
the memory is used for storing programs;
the processor is configured to execute the program to implement the steps of the method for naming an electronic image as described above.
A readable storage medium, on which a computer program is stored, characterized in that said computer program, when being executed by a processor, carries out the steps of the method for naming electronic images as described above.
It can be seen from the foregoing technical solutions that, in the method, the apparatus, the device, and the readable storage medium for naming an electronic image provided in the embodiments of the present application, a first name is obtained, where the first name is a name of a first electronic image, and if the first name is consistent with a name of an associated attachment of a second electronic image, the name of the first electronic image is modified from the first name to a name of the second electronic image, where the first electronic image and the second electronic image belong to a same image sequence, and the second electronic image is an adjacent image that is ordered before the first electronic image. Therefore, compared with the manual naming and sequencing method in the prior art, the method automatically acquires the name of each electronic image in the image sequence, modifies the name of the electronic image according to the incidence relation between adjacent electronic images, improves the naming efficiency, and enables the naming of the image to more accurately accord with the preset rule.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flowchart of a naming method of an electronic image according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a method for naming an electronic image according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a naming device for electronic images according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a naming device for electronic images according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The electronic image naming method provided by the embodiment of the application is applied to but not limited to the scene of naming the electronic images under the same folder, for example, in the real estate transaction process, identification information, contract information, real estate information and the like of all involved transaction parties, and electronic images obtained after scanning all paper documents.
Fig. 1 is a schematic flowchart of a naming method of an electronic image according to an embodiment of the present application. As shown in fig. 1, the method specifically includes S101 to S107.
S101, inputting the first electronic image into a preset classification model to obtain a name to be selected of the first electronic image output by the classification model.
In this embodiment, the classification model is configured to select a candidate name of the first electronic image and a confidence of the selected candidate name from a plurality of preset names according to a feature of the first electronic image.
It should be noted that the classification model includes a pre-trained CNN model, the input of the CNN model is a first electronic image, the output prediction result is a category number to which the first electronic image belongs and a confidence of the category number, any category number corresponds to a preset name, the classification model further queries and outputs a name corresponding to the category number to which the first electronic image belongs from a preset corresponding relationship, the name is used as a candidate name of the first electronic image, and the confidence of the category number is output as the confidence of the candidate name.
In this embodiment, the correspondence between the preset name and the category number may be a key-value correspondence stored in a file, a database, or a program data structure. For example, in a key-value pair storage manner existing in a database manner, the correspondence between the preset name and the category number is represented as the following table 1:
TABLE 1
| class_type | class_name |
| 001 | Trade application form |
| 002 | Identity card |
| 003 | Transaction contract |
| … | … |
In the table, class _ type represents a class number, and class _ name represents a name.
The CNN model training process mainly comprises the following steps:
and A1, acquiring the sample data set.
In this embodiment, the sample data set includes sample images with labels, where the label of any one sample image is the category number of the sample image.
A2, dividing the training data set into a training set and a verification set.
And A3, preprocessing the sample image, and setting the size of the sample image to be a preset size.
In this embodiment, the preprocessing process includes augmentation operations such as rotation and scaling.
And A4, inputting the sample images in the training set into the CNN model, and outputting the labels of the sample images and the confidence degrees 1 of the labels as targets to train the CNN model.
And A5, inputting the sample images in the verification set into the CNN model, and comparing the output prediction result with the labels of the sample images to obtain a verification result.
And if the verification result does not meet the preset condition, adjusting the model according to the verification result, and returning to A4 to train the CNN model.
And if the verification result meets the preset condition, stopping training to obtain a trained CNN model as a classification model.
It should be noted that the specific method of training can be referred to the prior art.
In this embodiment, the names to be selected of the preset values output by the classification model and the corresponding confidence levels are obtained, where the preset values may be set as needed.
S102, the name to be selected with the confidence coefficient not smaller than a preset threshold value is used as a first name.
In this embodiment, when the number of the names to be selected whose confidence is not less than the preset threshold is greater than 1, the name to be selected whose confidence is the largest is selected as the first name, that is, the name of the first electronic image.
S103, if the confidence coefficient of the name to be selected is smaller than a preset threshold value, character recognition is carried out on the preset area of the first electronic image, and recognition content is obtained.
In this embodiment, when the confidence of the name to be selected is smaller than the preset threshold value, which indicates that the prediction result of the classification model is inaccurate, the name to be selected is discarded.
In this embodiment, the preset region includes a header region and/or a first text region in the electronic image, for example, first, the header region of the electronic image is subjected to character recognition to determine the recognition content, and when the electronic image does not include the header region, the text in the first text region is subjected to character recognition to determine the recognition content. It should be noted that, the method for recognizing the preset area and the text can be referred to in the prior art, and the recognition content is the recognition name of the first electronic image obtained through recognition.
And S104, taking the preset name matched with the identification content as a first name.
In this embodiment, the matching process of the identification content and the preset name includes:
for the identification content (marked as first-class identification content) determined by identifying the title area, matching the first-class identification content with a plurality of preset names through a matching algorithm (fuzzy matching or editing distance), and taking the name with the highest matching degree as a first name, namely the name of the first electronic image.
For the identification content (recorded as the second type identification content) determined by identifying the first text region, the preset name satisfying the preset correspondence with the second type identification content is used as the first name, and it should be noted that, in this embodiment, the correspondence rule is preset according to the type of the file to which the electronic image belongs.
It should be noted that, S101 to S104 are optional methods for obtaining the name of the first electronic image (first name), and in practical application, there may be other methods.
S105, if the first name is consistent with the name of the associated attachment of the second electronic image, modifying the name of the first electronic image from the first name to the name of the second electronic image.
It should be noted that the corresponding relationship between the index number, the category number, the name, and the category number of the corresponding associated attachment of any electronic image is pre-stored as a preset ordering rule in the format of a database or a file format, and the ordering rule in this embodiment is determined according to the type to which the electronic images in the image sequence belong, the image sequence is electronic images arranged according to a preset sequence, the type to which the electronic images belong generally belongs to the field to which the electronic image content belongs, for example, the ordering rule of the real estate transaction type archive stored in the file format is as follows:
001-1 ═ -land property registration examination and check table
002-2 ═ real estate transaction authority ownership registration approval sheet
003-2 ═ -nation has the right to use land and give agreement +6| 10-
004-3-real estate registration application form
005-3-real estate transaction contract registration application form
006-4 ═ on-site registration survey chart
Site survey table for 007-4 ═ -land property registration center
008-5 ═ real estate area measurement report
009-5 ═ -real estate estimate report
010-6 ═ identity card
001-6 ═ -civil court performance official business certificate
011-7 ═ french for representative certificate
012-7 ═ -business entity legal certificate
013-8 ═ family mouth book
014-9 ═ -birth medicine proof
015-10 ═ business license
016-10 ═ organizational code certificate
017-11 ═ group purchase contract +6|8|10 utiventilation
Here, "-" "+" "|" is a space symbol, and for example, "003-2" - "national land use right giving contract +6|10 |", the "003" is an index symbol, and the order of the electronic images which are named "national land use right giving contract" is the third digit, "2" is a category number, "national land use right giving contract" is a name, "6 | 10" is a category number "6" and "10" of the associated attachment corresponding to the electronic image which is named "national land use right giving contract", that is, two types of images of 6 and 10 are allowed to appear behind the category 2.
In this embodiment, the first name being identical to the name of the associated attachment of the second electronic image means that the category number of the first name is the same as the category number of the associated attachment corresponding to the name of the second electronic image. It should be noted that the first electronic image and the second electronic image belong to the same image sequence, and the second electronic image is an adjacent image ordered before the first electronic image. Any image sequence comprises a plurality of electronic images which are arranged in sequence.
For example, the first name is an identification card, the name of the second electronic image is a national land use right giving contract, and the second image is an adjacent image located before the first electronic image in the image sequence, so that, as can be seen from the above-mentioned sorting rule of the real estate transaction type profile, the category number of the associated attachment of the second electronic image includes the category number of the identification card, so the embodiment modifies the first name from the identification card to the national land use right giving contract.
In this embodiment, it is sequentially determined whether the name of each electronic image matches the name of the associated attachment of the previous adjacent electronic image in the order of the image sequence, and if so, the name of the electronic image is modified to the name of the previous adjacent electronic image.
And S106, if the sequence of the names in the name sequence is different from the preset sequencing rule, sending a modification prompt.
The name sequence is the name of the electronic images in the image sequence, and is formed by arranging the names according to the sequence of the electronic images.
In this embodiment, starting from a name in the order of 1 in the name sequence, it is checked whether the index number corresponding to the next name is after the index number corresponding to the previous name. And if the index number corresponding to at least one name is not behind the index number corresponding to the previous name, determining the order of the names in the name sequence, wherein the order is different from the preset ordering rule.
In this embodiment, the modification prompt includes a verification failure prompt and/or a name of the electronic image with the wrong rank.
And S107, if the sequence of the names in the name sequence is the same as the preset sequencing rule, storing the electronic images according to the names of the electronic images.
When the index numbers corresponding to all names in the name sequence are arranged from small to large, the order of the names in the name sequence is determined to be the same as the preset ordering rule, and the electronic image is stored according to the name of the electronic image.
According to the technical scheme, the electronic image naming method provided by the embodiment of the application obtains the first name, the first name is the name of the first electronic image, and if the first name is consistent with the name of the associated attachment of the second electronic image, the name of the first electronic image is modified from the first name to the name of the second electronic image, wherein the first electronic image and the second electronic image belong to the same image sequence, and the second electronic image is an adjacent image sequenced before the first electronic image. Therefore, compared with the manual naming and sequencing method in the prior art, the method automatically acquires the name of each electronic image in the image sequence, modifies the name of the electronic image according to the incidence relation between adjacent electronic images, improves the naming efficiency, and enables the naming of the image to more accurately accord with the preset rule.
Furthermore, when the first name is obtained, the method combining the classification model and the text recognition is applied, and the accuracy of name recognition is improved.
Furthermore, the method verifies whether the order of the names in the name sequence is correct according to the sorting rule, and if the order of the names in the name sequence is incorrect, a modification prompt is sent out, so that the accuracy of image naming is improved.
It should be noted that the flow shown in fig. 1 is only an optional specific implementation method of the electronic image naming method provided in the embodiment of the present application, for example, S106 to S107 are inspection processes and are optional steps, the embodiment summarizes the electronic image naming method group as fig. 2, and fig. 2 is a schematic flow diagram of another electronic image naming method provided in the embodiment of the present application, and may specifically include S201 to S202.
S201, acquiring a first name.
In this embodiment, the first name is the name of the first electronic image, and the first electronic image is any one of a sequence of images.
It should be noted that the method for acquiring the first electronic image may include multiple methods, for example, inputting the first electronic image into a preset classification model, and obtaining the candidate name of the first electronic image output by the classification model. And taking the name to be selected with the confidence coefficient not less than the preset threshold value as a first name.
And if the confidence coefficient of the name to be selected is smaller than the preset threshold value, performing character recognition on the preset area of the first electronic image to obtain recognition content. And taking the preset name matched with the identification content as a first name.
See S101 to S104 for details.
S202, if the first name is consistent with the name of the associated attachment of the second electronic image, the name of the first electronic image is modified from the first name to the name of the second electronic image.
In this embodiment, the first electronic image and the second electronic image belong to the same image sequence, and the second electronic image is an adjacent image ordered before the first electronic image.
The associated attachments to the second electronic image are images of files that may be attachments to the second electronic image, for example, the second electronic image is an electronic image of a group purchase contract, and the associated attachments to the group purchase contract may be an electronic image of an identification card, and/or an electronic image of a family account, and/or an electronic image of an organization code card. It should be noted that the name of the electronic image and the name of the associated attachment of the electronic image may be stored.
In this embodiment, if the first name is consistent with the name of the associated attachment of the second electronic image, it is determined that the first electronic image is the associated attachment of the second electronic image, and the name of the first electronic image is modified to the name of the second electronic image.
It should be noted that the image sequence includes a plurality of electronic images, in this embodiment, it is sequentially determined according to the sequence of the image sequence whether the name of each electronic image is consistent with the name of the associated attachment of the previous adjacent electronic image, and if so, the name of the electronic image is modified into the name of the previous adjacent electronic image.
According to the technical scheme, the electronic image naming method provided by the embodiment of the application obtains the first name, the first name is the name of the first electronic image, and if the first name is consistent with the name of the associated attachment of the second electronic image, the name of the first electronic image is modified from the first name to the name of the second electronic image, wherein the first electronic image and the second electronic image belong to the same image sequence, and the second electronic image is an adjacent image sequenced before the first electronic image. Therefore, compared with the manual naming and sequencing method in the prior art, the method automatically acquires the name of each electronic image in the image sequence, modifies the name of the electronic image according to the incidence relation between adjacent electronic images, improves the naming efficiency, and enables the naming of the image to more accurately accord with the preset rule.
Fig. 3 is a schematic structural diagram of an electronic image naming device provided in an embodiment of the present application, and as shown in fig. 3, the device may include:
a name acquisition unit 301 for acquiring a first name which is a name of a first electronic image;
and a name modifying unit 302, configured to modify a name of the first electronic image from the first name to a name of the second electronic image if the first name is consistent with a name of an associated attachment of the second electronic image, where the first electronic image and the second electronic image belong to a same image sequence, and the second electronic image is an adjacent image that is ordered before the first electronic image.
Optionally, the apparatus further comprises:
a modification prompt unit to: if the order of the names in the name sequence is different from the preset ordering rule, sending a modification prompt;
the name sequence is the name of an electronic image in the image sequence, the sequence is formed by arranging the names according to the sequence of the electronic images, and the sequencing rule is determined according to the type of the electronic image in the image sequence.
Optionally, the ordering rule comprises:
the method comprises the steps of obtaining the corresponding relation of an index number, a category number, a name and the category number of an associated accessory, wherein the index number is used for indicating the sequence of the name.
Optionally, the first name is identical to a name of an associated attachment to the second electronic image, including:
the category number of the first name is the same as the category number of the associated attachment corresponding to the name of the second electronic image.
Optionally, the apparatus further comprises:
an image storage unit configured to: and if the sequence of the names in the name sequence is the same as the preset sequencing rule, storing the electronic image according to the name of the electronic image.
Optionally, the name obtaining unit is configured to obtain the first name, and includes: the name acquisition unit is specifically configured to:
inputting the first electronic image into a preset classification model to obtain a name to be selected of the first electronic image output by the classification model;
the classification model is used for selecting the name to be selected of the first electronic image and the confidence coefficient of the selected name from a plurality of preset names according to the characteristics of the first electronic image;
and taking the name to be selected with the confidence coefficient not less than a preset threshold value as the first name.
Optionally, the apparatus further comprises:
a character recognition unit for: if the confidence coefficient of the name to be selected is smaller than the preset threshold value, character recognition is carried out on the preset area of the first electronic image, and recognition content is obtained;
and taking the preset name matched with the identification content as the first name.
An embodiment of the present application further provides a naming device of an electronic image, please refer to fig. 4, which shows a schematic structural diagram of the naming device of the electronic image, and the device may include: at least one processor 401, at least one communication interface 402, at least one memory 403 and at least one communication bus 404;
in the embodiment of the present application, the number of the processor 401, the communication interface 402, the memory 403 and the communication bus 404 is at least one, and the processor 401, the communication interface 402 and the memory 403 complete communication with each other through the communication bus 404;
the processor 401 may be a central processing unit CPU, or an application specific Integrated circuit asic, or one or more Integrated circuits configured to implement embodiments of the present invention, or the like;
the memory 403 may include a high-speed RAM memory, and may further include a non-volatile memory (non-volatile memory) or the like, such as at least one disk memory;
the memory stores programs, and the processor can execute the programs stored in the memory to realize the electronic image naming method provided by the embodiment of the application, and the electronic image naming method comprises the following steps:
obtaining a first name, the first name being a name of a first electronic image;
and if the first name is consistent with the name of the associated attachment of the second electronic image, modifying the name of the first electronic image from the first name into the name of the second electronic image, wherein the first electronic image and the second electronic image belong to the same image sequence, and the second electronic image is an adjacent image sequenced before the first electronic image.
Optionally, the method further comprises:
if the order of the names in the name sequence is different from the preset ordering rule, sending a modification prompt;
the name sequence is the name of an electronic image in the image sequence, the sequence is formed by arranging the names according to the sequence of the electronic images, and the sequencing rule is determined according to the type of the electronic image in the image sequence.
Optionally, the ordering rule comprises:
the method comprises the steps of obtaining the corresponding relation of an index number, a category number, a name and the category number of an associated accessory, wherein the index number is used for indicating the sequence of the name.
Optionally, the first name is identical to a name of an associated attachment to the second electronic image, including:
the category number of the first name is the same as the category number of the associated attachment corresponding to the name of the second electronic image.
Optionally, the method further comprises:
and if the sequence of the names in the name sequence is the same as the preset sequencing rule, storing the electronic image according to the name of the electronic image.
Optionally, obtaining the first name includes:
inputting the first electronic image into a preset classification model to obtain a name to be selected of the first electronic image output by the classification model;
the classification model is used for selecting the name to be selected of the first electronic image and the confidence coefficient of the selected name from a plurality of preset names according to the characteristics of the first electronic image;
and taking the name to be selected with the confidence coefficient not less than a preset threshold value as the first name.
Optionally, the method further comprises:
if the confidence coefficient of the name to be selected is smaller than the preset threshold value, character recognition is carried out on the preset area of the first electronic image, and recognition content is obtained;
and taking the preset name matched with the identification content as the first name.
Embodiments of the present application further provide a readable storage medium, where the readable storage medium may store a computer program adapted to be executed by a processor, and when the computer program is executed by the processor, the computer program implements a naming method of an electronic image provided in an embodiment of the present application, as follows:
obtaining a first name, the first name being a name of a first electronic image;
and if the first name is consistent with the name of the associated attachment of the second electronic image, modifying the name of the first electronic image from the first name into the name of the second electronic image, wherein the first electronic image and the second electronic image belong to the same image sequence, and the second electronic image is an adjacent image sequenced before the first electronic image.
Optionally, the method further comprises:
if the order of the names in the name sequence is different from the preset ordering rule, sending a modification prompt;
the name sequence is the name of an electronic image in the image sequence, the sequence is formed by arranging the names according to the sequence of the electronic images, and the sequencing rule is determined according to the type of the electronic image in the image sequence.
Optionally, the ordering rule comprises:
the method comprises the steps of obtaining the corresponding relation of an index number, a category number, a name and the category number of an associated accessory, wherein the index number is used for indicating the sequence of the name.
Optionally, the first name is identical to a name of an associated attachment to the second electronic image, including:
the category number of the first name is the same as the category number of the associated attachment corresponding to the name of the second electronic image.
Optionally, the method further comprises:
and if the sequence of the names in the name sequence is the same as the preset sequencing rule, storing the electronic image according to the name of the electronic image.
Optionally, obtaining the first name includes:
inputting the first electronic image into a preset classification model to obtain a name to be selected of the first electronic image output by the classification model;
the classification model is used for selecting the name to be selected of the first electronic image and the confidence coefficient of the selected name from a plurality of preset names according to the characteristics of the first electronic image;
and taking the name to be selected with the confidence coefficient not less than a preset threshold value as the first name.
Optionally, the method further comprises:
if the confidence coefficient of the name to be selected is smaller than the preset threshold value, character recognition is carried out on the preset area of the first electronic image, and recognition content is obtained;
and taking the preset name matched with the identification content as the first name.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for naming an electronic image, comprising:
obtaining a first name, the first name being a name of a first electronic image;
and if the first name is consistent with the name of the associated attachment of the second electronic image, modifying the name of the first electronic image from the first name into the name of the second electronic image, wherein the first electronic image and the second electronic image belong to the same image sequence, and the second electronic image is an adjacent image sequenced before the first electronic image.
2. The method of claim 1, further comprising:
if the order of the names in the name sequence is different from the preset ordering rule, sending a modification prompt;
the name sequence is the name of an electronic image in the image sequence, the sequence is formed by arranging the names according to the sequence of the electronic images, and the sequencing rule is determined according to the type of the electronic image in the image sequence.
3. The method of claim 2, wherein the ordering rule comprises:
the method comprises the steps of obtaining the corresponding relation of an index number, a category number, a name and the category number of an associated accessory, wherein the index number is used for indicating the sequence of the name.
4. The method of claim 3, wherein the first name is consistent with a name of an associated attachment to the second electronic image, comprising:
the category number of the first name is the same as the category number of the associated attachment corresponding to the name of the second electronic image.
5. The method of claim 2, further comprising:
and if the sequence of the names in the name sequence is the same as the preset sequencing rule, storing the electronic image according to the name of the electronic image.
6. The method of claim 1, wherein obtaining the first name comprises:
inputting the first electronic image into a preset classification model to obtain a name to be selected of the first electronic image output by the classification model;
the classification model is used for selecting the name to be selected of the first electronic image and the confidence coefficient of the selected name from a plurality of preset names according to the characteristics of the first electronic image;
and taking the name to be selected with the confidence coefficient not less than a preset threshold value as the first name.
7. The method of claim 6, further comprising:
if the confidence coefficient of the name to be selected is smaller than the preset threshold value, character recognition is carried out on the preset area of the first electronic image, and recognition content is obtained;
and taking the preset name matched with the identification content as the first name.
8. An electronic image naming apparatus, comprising:
a name acquisition unit configured to acquire a first name that is a name of a first electronic image;
and the name modifying unit is used for modifying the name of the first electronic image into the name of the second electronic image from the first name if the first name is consistent with the name of the associated attachment of the second electronic image, wherein the first electronic image and the second electronic image belong to the same image sequence, and the second electronic image is an adjacent image sequenced before the first electronic image.
9. An electronic image naming apparatus, comprising: a memory and a processor;
the memory is used for storing programs;
the processor, which executes the program, realizes the steps of the electronic image naming method according to any one of claims 1 to 7.
10. A readable storage medium, on which a computer program is stored, characterized in that said computer program, when being executed by a processor, carries out the steps of the method for naming electronic images as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010777838.7A CN111858500A (en) | 2020-08-05 | 2020-08-05 | Electronic image naming method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010777838.7A CN111858500A (en) | 2020-08-05 | 2020-08-05 | Electronic image naming method, device, equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111858500A true CN111858500A (en) | 2020-10-30 |
Family
ID=72971346
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010777838.7A Pending CN111858500A (en) | 2020-08-05 | 2020-08-05 | Electronic image naming method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111858500A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104572847A (en) * | 2014-12-15 | 2015-04-29 | 广东欧珀移动通信有限公司 | Method and device for naming photo |
| CN105260428A (en) * | 2015-09-29 | 2016-01-20 | 北京奇艺世纪科技有限公司 | Picture processing method and apparatus |
| CN106101545A (en) * | 2016-06-30 | 2016-11-09 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| JP2019153919A (en) * | 2018-03-02 | 2019-09-12 | キヤノン株式会社 | Image processing device, control method thereof, and program |
| CN110941443A (en) * | 2019-12-12 | 2020-03-31 | 支付宝(杭州)信息技术有限公司 | Method and device for modifying file name in SDK and electronic equipment |
| CN111242230A (en) * | 2020-01-17 | 2020-06-05 | 腾讯科技（深圳）有限公司 | Image processing method and image classification model training method based on artificial intelligence |
| CN111461195A (en) * | 2020-03-27 | 2020-07-28 | 国网电子商务有限公司 | Picture checking method and device and electronic equipment |
-
2020
- 2020-08-05 CN CN202010777838.7A patent/CN111858500A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104572847A (en) * | 2014-12-15 | 2015-04-29 | 广东欧珀移动通信有限公司 | Method and device for naming photo |
| CN105260428A (en) * | 2015-09-29 | 2016-01-20 | 北京奇艺世纪科技有限公司 | Picture processing method and apparatus |
| CN106101545A (en) * | 2016-06-30 | 2016-11-09 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| JP2019153919A (en) * | 2018-03-02 | 2019-09-12 | キヤノン株式会社 | Image processing device, control method thereof, and program |
| CN110941443A (en) * | 2019-12-12 | 2020-03-31 | 支付宝(杭州)信息技术有限公司 | Method and device for modifying file name in SDK and electronic equipment |
| CN111242230A (en) * | 2020-01-17 | 2020-06-05 | 腾讯科技（深圳）有限公司 | Image processing method and image classification model training method based on artificial intelligence |
| CN111461195A (en) * | 2020-03-27 | 2020-07-28 | 国网电子商务有限公司 | Picture checking method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109101469B (en) | Extracting searchable information from digitized documents | |
| CN114117171B (en) | Intelligent project file collecting method and system based on energized thinking | |
| CN111767422A (en) | Data auditing method, device, terminal and storage medium | |
| US20050210047A1 (en) | Posting data to a database from non-standard documents using document mapping to standard document types | |
| CN108764707A (en) | A kind of data assessment system and method | |
| US20050210016A1 (en) | Confidence-based conversion of language to data systems and methods | |
| US20190286896A1 (en) | System and method for automatic detection and verification of optical character recognition data | |
| JP2007026386A (en) | Image search system and method | |
| CN110688349B (en) | Document sorting method, device, terminal and computer readable storage medium | |
| US10949610B2 (en) | Computing machine and template management method | |
| CN110188077B (en) | Intelligent classification method and device for electronic files, electronic equipment and storage medium | |
| WO2015015826A1 (en) | Document classification system, document classification method, and document classification program | |
| CN111899090B (en) | Enterprise associated risk early warning method and system | |
| CN110851591A (en) | Judgment document quality evaluation method, device, equipment and storage medium | |
| CN112632989A (en) | Method, device and equipment for prompting risk information in contract text | |
| CN115116068B (en) | Archive intelligent archiving system based on OCR | |
| US20050210046A1 (en) | Context-based conversion of language to data systems and methods | |
| WO2022134580A1 (en) | Method and apparatus for acquiring certificate information, and storage medium and computer device | |
| TW201508525A (en) | Document sorting system, document sorting method, and document sorting program | |
| CN117036073B (en) | Invoice auditing and automatic reimbursement system based on Internet | |
| CN115687790B (en) | Advertisement pushing method and system based on big data and cloud platform | |
| CN111858500A (en) | Electronic image naming method, device, equipment and readable storage medium | |
| CN114638597A (en) | Intelligent government affair handling application system, method, terminal and medium | |
| CN114743048A (en) | Method and device for detecting abnormal straw picture | |
| CN115470177A (en) | File processing method, device, equipment and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |