WO2022111461A1 - 识别方法、装置及电子设备 - Google Patents

识别方法、装置及电子设备 Download PDF

Info

Publication number
WO2022111461A1
WO2022111461A1 PCT/CN2021/132368 CN2021132368W WO2022111461A1 WO 2022111461 A1 WO2022111461 A1 WO 2022111461A1 CN 2021132368 W CN2021132368 W CN 2021132368W WO 2022111461 A1 WO2022111461 A1 WO 2022111461A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
identification
recognition result
content
result
Prior art date
Application number
PCT/CN2021/132368
Other languages
English (en)
French (fr)
Inventor
李意敏
Original Assignee
维沃移动通信有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 维沃移动通信有限公司 filed Critical 维沃移动通信有限公司
Publication of WO2022111461A1 publication Critical patent/WO2022111461A1/zh
Priority to US18/203,049 priority Critical patent/US20230306765A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/14—Image acquisition
    • G06V30/141—Image acquisition using multiple overlapping images; Image stitching
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/67—Focus control based on electronic image sensor signals
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/70—Circuitry for compensating brightness variation in the scene
    • H04N23/71—Circuitry for evaluating the brightness variation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/70—Circuitry for compensating brightness variation in the scene
    • H04N23/73—Circuitry for compensating brightness variation in the scene by influencing the exposure time
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/70—Circuitry for compensating brightness variation in the scene
    • H04N23/75—Circuitry for compensating brightness variation in the scene by influencing optical camera components

Definitions

  • the present application belongs to the field of communication technologies, and specifically relates to an identification method, an apparatus and an electronic device.
  • scanning recognition is generally used to improve the conversion efficiency of the documents.
  • there will be reflective areas in the scanned image of the scanned document resulting in unclear parts in the recognition result due to the existence of reflective areas in the process of recognizing the scanned image.
  • the purpose of the embodiments of the present application is to provide a recognition method, device and electronic device, which can solve the problem of poor recognition effect in the content recognition of the image when the image has a reflective area.
  • an embodiment of the present application provides an identification method, including:
  • the captured first image includes a reflective area
  • the shooting parameters include at least one of aperture and focus
  • the target image includes the second image, or the target image is obtained according to the first image and the second image.
  • an identification device including:
  • an adjustment module configured to adjust a shooting parameter of the camera when the captured first image includes a reflective area, where the shooting parameter includes at least one of aperture and focus;
  • an acquisition module configured to acquire a second image according to the adjusted shooting parameters
  • the recognition module is used to recognize the target image and obtain the corresponding recognition result
  • the target image includes the second image, or the target image is obtained according to the first image and the second image.
  • embodiments of the present application provide an electronic device, the electronic device includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor, the program or instruction being The processor implements the steps of the method according to the first aspect when executed.
  • an embodiment of the present application provides a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the method according to the first aspect are implemented .
  • an embodiment of the present application provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or an instruction, and implement the first aspect the method described.
  • an embodiment of the present application provides a program product, the program product is stored in a non-volatile storage medium, and the program product is executed by at least one processor to implement the method according to the first aspect. step.
  • an embodiment of the present application provides a communication device configured to perform the steps of the method described in the first aspect.
  • the reflection of the feature information corresponding to the reflective area can be eliminated or reduced by adjusting the shooting parameters, so as to collect the corresponding second image, thereby reducing the In the process of image recognition, the influence of the reflective area on the recognition result improves the accuracy of the recognition result.
  • Fig. 2a is one of the operation schematic diagrams provided by the embodiment of the present application.
  • FIG. 2b is the second schematic diagram of operation provided by the embodiment of the present application.
  • Fig. 2c is the third schematic diagram of operation provided by the embodiment of the present application.
  • FIG. 3 is a structural diagram of an identification device provided by an embodiment of the present application.
  • FIG. 4 is a structural diagram of an electronic device provided by an embodiment of the present application.
  • FIG. 5 is a structural diagram of an electronic device provided by another embodiment of the embodiment of the present application.
  • first, second and the like in the description and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances so that the embodiments of the present application can be practiced in sequences other than those illustrated or described herein, and distinguish between “first”, “second”, etc.
  • the objects are usually of one type, and the number of objects is not limited.
  • the first object may be one or more than one.
  • “and/or” in the description and claims indicates at least one of the connected objects, and the character “/" generally indicates that the associated objects are in an "or” relationship.
  • FIG. 1 is a flowchart of an identification method provided by an embodiment of the present application.
  • the identification method provided by an embodiment of the present application can be applied to an electronic device including a camera. As shown in FIG. 1, the identification method includes the following steps:
  • Step 101 In the case that the captured first image includes a reflective area, adjust the shooting parameters of the camera.
  • the shooting parameters include at least one of aperture and focus, that is, reflections can be eliminated or reduced by adjusting the aperture and focus of the camera, so as to capture a corresponding image.
  • the image of the target object in the process of scanning and recognizing the target object, can be collected first, and then the content of the image can be recognized; if in the process of recognizing the content of the image, it is recognized that there is a reflective area in the image, then go to step 101, in order to capture the corresponding images.
  • the target object may be a document or a picture.
  • the scanned image of the document can be collected first; after the scanned image of the document is collected, the scanned image can be extracted by extracting the features of the text area. image for identification.
  • the text area features include the texture, color difference, light, and contrast characteristics of the color difference between the front and the back of the scanned image.
  • key feature information can be extracted from the place where the contour curvature of the scanned image is the largest or the contour feature, so as to determine whether there is a reflective area or a curved surface area in the scanned image.
  • a reflective photo confirmed by the user can be collected as a reference object, and key feature information of the scanned image can be extracted, and the extracted key feature information can be compared with the key feature information at the same location as the reference object.
  • the standardized key feature information forms the reference object feature vector a and the undetermined photo feature vector b respectively, and the similarity between the key feature information vectors a and b is calculated; for example, the similarity can be taken as the second norm of a and b, if the similarity Within a certain threshold range, it is determined that there is a reflective area in the scanned image.
  • the shooting parameters of the camera can be adjusted to reduce or eliminate the reflection of the document, so as to capture a corresponding image.
  • Step 102 Collect a second image according to the adjusted shooting parameters.
  • the second image may be an image associated with the reflective area, that is, by adjusting the shooting parameters, to reduce or eliminate the reflective of the feature information corresponding to the reflective area, so as to collect the corresponding second image.
  • the reflection of feature A of the target object can be reduced or eliminated by adjusting the shooting parameters, so that the image corresponding to feature A in the collected second image can be reduced or eliminated. Areas are not reflective.
  • Step 103 Recognize the target image to obtain a corresponding recognition result.
  • the target image includes the second image, or the target image is obtained according to the first image and the second image.
  • the second image may be an overall scanned image of the target object, and there is no reflective area in the second image, so the second image can be identified to obtain the target object corresponding recognition results.
  • the target image includes a first image and a second image
  • the second image is only a partial scanned image of the target object
  • the second image may only correspond to the image features associated with the reflective area in the first image.
  • the content of the first image and the content of the second image can be respectively identified, and synthesis processing is performed based on the identified content to obtain the identification result corresponding to the target object.
  • the first image and the second image can be fused to obtain the target image, and then the target image can be recognized to obtain the corresponding recognition result.
  • the captured first image includes a reflective area
  • the impact on the recognition results and the accuracy of the recognition results are improved.
  • the target object may also include other scanned images.
  • the scanned image including the curved area may be tiled, so as to identify the scanned image including the curved area;
  • the scanned image including the blurred area can be deblurred, so as to identify the scanned image including the blurred area. This can improve the accuracy of the recognition results of other scanned images.
  • the recognition result corresponding to the target image and the recognition results corresponding to other scanned images of the target object can be combined to obtain the recognition result of the target object.
  • the recognition content of the common area between the images can be used as the connection position for merging, so as to improve the accuracy of the merging process, and further Improve the accuracy of recognition results.
  • the target image includes the first image and the second image, and the target image is identified to obtain a corresponding identification result, including:
  • the first identification result and the second identification result are combined to obtain the identification result corresponding to the target image.
  • the identification content of the public area may be used as the connection content of the first identification result and the second identification result, so as to improve the accuracy of the merging process and further improve the accuracy of the identification result.
  • the target object is a document
  • the character information in the first image can be recognized, and the position information of each character can also be recorded to obtain the first recognition result;
  • the character information in the second image can also be recognized, and the position information of each character can be recorded to obtain the second recognition result.
  • the determining the identification content of the common area of the first image and the second image based on the first identification result and the second identification result includes: obtaining the identification content in the first identification result. Character information and position information of the first character; obtain character information and position information of the second character in the second recognition result; character information and position information of the first character and character information of the second character and When the location information is the same, the first character or the second character is used as the identification content of the common area of the first image and the second image.
  • the position information of the character can be determined by calculating the line number and coordinate information of the character.
  • character information distributed in four squares of each character can be recorded, one or more characters can be recorded in each direction, and the specific number can be adjusted according to actual needs to ensure that each character is adjacent to each other as much as possible.
  • the uniqueness of the character distribution thus ensuring the accuracy of the character position information.
  • the first recognition result and the second recognition result are combined based on the recognition content of the public area to obtain the recognition result corresponding to the target image, including:
  • the first identification result and the second identification result are merged to obtain a merged identification result
  • the combined recognition result is checked to obtain the recognition result corresponding to the target image.
  • the online search function can be used to obtain the content associated with the identification result, that is, obtain the content with high similarity with the identification result, and verify the combined identification result to avoid identification The lack of results to further improve the accuracy of the recognition results.
  • the first and second contents obtained by the retrieval can be used to supplement the combined recognition result or Replacement to improve the integrity of the merged recognition results.
  • the method further includes:
  • the second image includes a curved area, performing tiling processing on the second image
  • the target image includes the second image after tiling processing, or the target image is obtained according to the first image and the second image after tiling processing.
  • the second image may be tiled to reduce the influence of the curved area on the recognition result of the second image.
  • the surface features of the surface area can be calculated, and the corresponding information can be transformed during the tiling process, so as to obtain the image features after the tiling process.
  • the blurred area in the second image may also be deblurred, so as to reduce the influence of the blurred area on the recognition result.
  • the cause of the blurred area is mainly blur caused by shooting; for the blurred area formed by shooting, deblurring can be performed in a smoothing and strengthening manner.
  • the user can select a shooting strategy to reduce the influence of the curved surface on the recognition result of the target object.
  • the target object is a document.
  • the sequence of shooting angles can be selected, and the scanned image of the target object can be collected from left to right; for example, the content of the left part of the target object can be collected first , and obtain the first scanned image 22 , as shown in FIG. 2 b ; and then collect the content of the right part of the target object, and obtain the second scanned image 23 , as shown in FIG. 2 c .
  • the first scanned image 22 and the second scanned image 23 can be recognized respectively, and text information can be extracted; in the process of recognizing and extracting text information, if any one of the first scanned image 22 and the second scanned image 23 exists In the case of a reflective area, steps 101 to 103 are performed to eliminate the influence of the reflective area on the recognition result.
  • a certain part of the target object can be photographed and identified, or the target object can be automatically divided into multiple objects according to the regional positions, and each object can be independently judged and identified.
  • the scanned image can be identified and extracted, the clear area in the scanned image can be identified, and the unclear area can be marked.
  • the identification information for the identified clear areas can be stored first; the unclear areas are marked and numbered; then, the unclear areas are re-shot to obtain their corresponding clear images; in the process of re-shooting , the shooting area can be selected based on the user's input operation, or the shooting area can be automatically selected based on the marker number.
  • the unclear area is a reflective area
  • the image features corresponding to the reflective area will be re-shot, and an image without reflection will be captured
  • the unclear area is a curved area
  • the curved area will be tiled to reduce The influence of the surface area on the recognition result
  • the unclear area is a fuzzy area
  • the fuzzy area can be de-blurred to reduce the influence of the fuzzy area on the recognition result.
  • the shooting parameters of the camera can be adjusted, such as setting different parameters such as aperture and focus, and multiple images can be taken and stored, as far as possible. Make every text area have at least one non-reflective image to get a non-reflective second image.
  • the shooting parameters of the camera are adjusted, and the shooting parameters include at least one of aperture and focus; according to the adjusted Shooting parameters, collecting a second image; recognizing the target image to obtain a corresponding recognition result; wherein the target image includes a second image, or the target image is obtained according to the first image and the second image .
  • the captured first image includes a reflective area
  • the impact on the recognition results and the accuracy of the recognition results are improved.
  • the execution subject may be an identification device, or a control module in the identification device for executing the identification method.
  • the identification device provided by the embodiment of the present application is described by taking the identification device executing the identification method as an example.
  • FIG. 3 is a structural diagram of an identification device provided by an embodiment of the present application. As shown in FIG. 3, the identification device 300 includes:
  • An adjustment module 301 configured to adjust the shooting parameters of the camera when the captured first image includes a reflective area, where the shooting parameters include at least one of aperture and focus;
  • an acquisition module 302 configured to acquire a second image according to the adjusted shooting parameters
  • the identification module 303 is used to identify the target image to obtain a corresponding identification result
  • the target image includes the second image, or the target image is obtained according to the first image and the second image.
  • the target image includes the first image and the second image
  • the identification module 303 includes:
  • a first identification unit configured to identify the first image to obtain a first identification result
  • a second identification unit configured to identify the second image to obtain a second identification result
  • a determining unit configured to determine the identification content of the common area of the first image and the second image based on the first identification result and the second identification result
  • a merging unit configured to perform merging processing on the first recognition result and the second recognition result based on the recognition content of the common area to obtain a recognition result corresponding to the target image.
  • the determining unit includes:
  • a first acquisition subunit used for acquiring character information and position information of the first character in the first recognition result
  • a second acquisition subunit used for acquiring character information and position information of the second character in the second recognition result
  • a determination subunit configured to use the first character or the second character as the The identification content of the common area of the first image and the second image.
  • the merging unit includes:
  • a merging subunit configured to perform merging processing on the first recognition result and the second recognition result based on the identification content of the public area to obtain a combined identification result
  • a third acquiring subunit configured to acquire the first content associated with the first recognition result and the second content associated with the second recognition result
  • a verification subunit configured to verify the combined identification result based on the first content and the second content to obtain the identification result corresponding to the target image.
  • the identification device 300 further includes:
  • a tiling module configured to perform tiling processing on the second image when the second image includes a curved surface area
  • the target image includes the second image after tiling processing, or the target image is obtained according to the first image and the second image after tiling processing.
  • the identification device in this embodiment of the present application may be a device, or may be a component, an integrated circuit, or a chip in a terminal.
  • the apparatus may be a mobile electronic device or a non-mobile electronic device.
  • the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a palmtop computer, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (personal digital assistant).
  • UMPC ultra-mobile personal computer
  • netbook or a personal digital assistant
  • the non-mobile electronic device may be a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., the embodiment of the present application There is no specific limitation.
  • Network Attached Storage NAS
  • personal computer personal computer, PC
  • television television
  • teller machine a self-service machine
  • the identification device in this embodiment of the present application may be a device with an operating system.
  • the operating system may be an Android (Android) operating system, an ios operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.
  • the identification device provided in this embodiment of the present application can implement each process implemented by the method embodiment in FIG. 1 , and to avoid repetition, details are not described here.
  • an embodiment of the present application further provides an electronic device 400, including a processor 401, a memory 402, and a program or instruction stored in the memory 402 and executable on the processor 401,
  • a processor 401 executes the program or instruction to execute the program or instruction.
  • the program or instruction is executed by the processor 401, each process of the above-mentioned embodiment of the identification method is implemented, and the same technical effect can be achieved. To avoid repetition, details are not described here.
  • the electronic devices in the embodiments of the present application include the above-mentioned mobile electronic devices and non-mobile electronic devices.
  • FIG. 5 is a structural diagram of an electronic device provided by an embodiment of the present application.
  • the electronic device 500 includes but is not limited to: a radio frequency unit 501, a network module 502, an audio output unit 503, and an input unit 504, a sensor 505, a display unit 506, a user input unit 507, an interface unit 508, a memory 509, and a processor 510 and other components.
  • the electronic device 500 may also include a power supply (such as a battery) for supplying power to various components, and the power supply may be logically connected to the processor 510 through a power management system, so that the power management system can manage charging, discharging, and power management. consumption management and other functions.
  • a power supply such as a battery
  • the structure of the electronic device shown in FIG. 5 does not constitute a limitation to the electronic device.
  • the electronic device may include more or less components than the one shown, or combine some components, or arrange different components, which will not be repeated here. .
  • the processor 510 is configured to adjust the shooting parameters of the camera when the captured first image includes a reflective area, and the shooting parameters include at least one of aperture and focus; the input unit 504 is configured to adjust the shooting parameters according to the The adjusted shooting parameters are used to collect a second image; the processor 510 is configured to identify the target image to obtain a corresponding identification result; wherein the target image includes the second image, or the target image Obtained from the first image and the second image.
  • the target image includes the first image and the second image
  • the processor 510 is configured to identify the first image to obtain a first identification result
  • the processor 510 is configured to identify the first image.
  • the second image is identified to obtain a second identification result
  • the processor 510 is configured to determine the identification of the common area of the first image and the second image based on the first identification result and the second identification result content
  • the processor 510 is configured to combine the first recognition result and the second recognition result based on the recognition content of the public area to obtain the recognition result corresponding to the target image.
  • the processor 510 is used to obtain character information and position information of the first character in the first recognition result; the processor 510 is used to obtain the character information and position of the second character in the second recognition result. information; the processor 510 is configured to, in the case that the character information and position information of the first character and the character information and position information of the second character are the same, the first character or the second character As the identification content of the common area of the first image and the second image.
  • the processor 510 is configured to combine the first identification result and the second identification result based on the identification content of the public area to obtain a combined identification result; the processor 510 is configured to obtain and The first content associated with the first identification result, and the second content associated with the second identification result; the processor 510 is configured to identify the combined identification based on the first content and the second content The result is verified, and the recognition result corresponding to the target image is obtained.
  • the processor 510 is configured to perform tiling processing on the second image when the second image includes a curved area; wherein, the target image includes the tiled first image Two images, or the target image is obtained from the first image and the tiled second image.
  • the input unit 504 may include a graphics processor (Graphics Processing Unit, GPU) 5041 and a microphone 5042. Such as camera) to obtain still pictures or video image data for processing.
  • the display unit 506 may include a display panel 5061, which may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like.
  • the user input unit 507 includes a touch panel 5071 and other input devices 5072 .
  • the touch panel 5071 is also called a touch screen.
  • the touch panel 5071 may include two parts, a touch detection device and a touch controller.
  • Other input devices 5072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which are not described herein again.
  • Memory 509 may be used to store software programs as well as various data, including but not limited to application programs and operating systems.
  • the processor 510 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the like, and the modem processor mainly processes wireless communication. It can be understood that, the above-mentioned modulation and demodulation processor may not be integrated into the processor 510.
  • Embodiments of the present application further provide a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, each process of the foregoing identification method embodiment can be achieved, and the same can be achieved.
  • the technical effect, in order to avoid repetition, will not be repeated here.
  • the processor is the processor in the electronic device described in the foregoing embodiments.
  • the readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.
  • An embodiment of the present application further provides a chip, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or an instruction to implement each of the foregoing identification method embodiments process, and can achieve the same technical effect, in order to avoid repetition, it will not be repeated here.
  • the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, a system-on-chip, a system-on-a-chip, or a system-on-a-chip, or the like.
  • the embodiments of the present application provide a computer program product, the program product is stored in a non-volatile storage medium, and the program product is executed by at least one processor to implement each process of the above method embodiments, and can achieve The same technical effect, in order to avoid repetition, will not be repeated here.
  • An embodiment of the present application provides a communication device, which is configured to perform each process of each embodiment of the above method, and can achieve the same technical effect. To avoid repetition, details are not repeated here.
  • the method of the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is better implementation.
  • the technical solution of the present application can be embodied in the form of a software product in essence or in a part that contributes to the prior art, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, CD-ROM), including several instructions to make a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of this application.
  • a storage medium such as ROM/RAM, magnetic disk, CD-ROM

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Studio Devices (AREA)

Abstract

本申请公开了一种识别方法、装置及电子设备，属于通信技术领域。该识别方法包括：在采集到的第一图像中包括反光区域的情况下，调整摄像头的拍摄参数，所述拍摄参数包括光圈、焦点中的至少一项；根据调整后的所述拍摄参数，采集第二图像；对目标图像进行识别，得到对应的识别结果；其中，所述目标图像包括所述第二图像，或者，所述目标图像根据所述第一图像和所述第二图像得到。

Description

识别方法、装置及电子设备
相关申请的交叉引用
本申请主张在2020年11月27日在中国提交的中国专利申请No.202011361267.5的优先权，其全部内容通过引用包含于此。
技术领域
本申请属于通信技术领域，具体涉及一种识别方法、装置及电子设备。
背景技术
目前，在将写一些印刷物等实体文档转化为电子文档的过程中，一般采用扫描识别的方式，以提高文档的转化效率。然而，在一些特殊的扫描场景下，被扫描文档的扫描图像会存在反光区域，导致在对扫描图像进行识别的过程中，会由于反光区域的存在，导致识别结果也存在不清楚的部分。
可见，在图像存在反光区域的情况下，图像的内容识别存在识别效果差的问题。
发明内容
本申请实施例的目的是提供一种识别方法、装置及电子设备，能够解决在图像存在反光区域的情况下，图像的内容识别存在识别效果差的问题。
为了解决上述技术问题，本申请是这样实现的：
第一方面，本申请实施例提供了一种识别方法，包括：
在采集到的第一图像中包括反光区域的情况下，调整摄像头的拍摄参数，所述拍摄参数包括光圈、焦点中的至少一项；
根据调整后的所述拍摄参数，采集第二图像；
对目标图像进行识别，得到对应的识别结果；
其中，所述目标图像包括所述第二图像，或者，所述目标图像根据所述第一图像和所述第二图像得到。
第二方面，本申请实施例提供了一种识别装置，包括：
调整模块，用于在采集到的第一图像中包括反光区域的情况下，调整摄像头的拍摄参数，所述拍摄参数包括光圈、焦点中的至少一项；
采集模块，用于根据调整后的所述拍摄参数，采集第二图像；
识别模块，用于对目标图像进行识别，得到对应的识别结果；
其中，所述目标图像包括所述第二图像，或者，所述目标图像根据所述第一图像和所述第二图像得到。
第三方面，本申请实施例提供了一种电子设备，该电子设备包括处理器、存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如第一方面所述的方法的步骤。
第四方面，本申请实施例提供了一种可读存储介质，所述可读存储介质上存储程序或指令，所述程序或指令被处理器执行时实现如第一方面所述的方法的步骤。
第五方面，本申请实施例提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现如第一方面所述的方法。
第六方面，本申请实施例提供一种程序产品，所述程序产品被存储在非易失的存储介质中，所述程序产品被至少一个处理器执行以实现如第一方面所述的方法的步骤。
第七方面，本申请实施例提供了一种通信设备，被配置为执行如第一方面所述的方法的步骤。
在本申请实施例中，在采集到的第一图像中包括反光区域的情况下，可以通过调整拍摄参数，消除或者减少反光区域对应的特征信息的反光，以便采集对应的第二图像，进而降低图像的识别过程中反光区域对识别结果的影响，提升识别结果的准确度。
附图说明
图1是本申请一实施例提供的识别方法的流程图；
图2a是本申请实施例提供的操作示意图之一；
图2b是本申请实施例提供的操作示意图之二；
图2c是本申请实施例提供的操作示意图之三；
图3是本申请实施例一实施例提供的识别装置的结构图；
图4是本申请实施例一实施例提供的电子设备的结构图；
图5是本申请实施例另一实施例提供的电子设备的结构图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作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。
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象，而不用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施，且“第一”、“第二”等所区分的对象通常为一类，并不限定对象的个数，例如第一对象可以是一个，也可以是多个。此外，说明书以及权利要求中“和/或”表示所连接对象的至少其中之一，字符“/”，一般表示前后关联对象是一种“或”的关系。
下面结合附图，通过具体的实施例及其应用场景对本申请实施例提供的识别方法进行详细地说明。
参见图1，图1是本申请一实施例提供的识别方法的流程图，本申请实施例提供的识别方法可以应用于包括摄像头的电子设备，如图1所示，该识别方法包括以下步骤：
步骤101、在采集到的第一图像中包括反光区域的情况下，调整摄像头的拍摄参数。
该步骤中，拍摄参数包括光圈、焦点中的至少一项，即可以通过调整摄像头的光圈、焦点的方式消除或者减少反光，以便采集对应的图像。
其中，在对目标对象进行扫描识别的过程中，可以先采集目标对象的图像，然后识别图像的内容；若在识别图像的内容的过程中，识别到图像中存在反光区域，则执行步骤101，以便采集对应的图像。
一个实施例中，目标对象可以是文档，也可以是图片。
比如，在目标对象为文档的情况下，在对文档进行扫描的识别的过程中，可以先采集文档的扫描图像；在采集到文档的扫描图像后，可以通过提取文字区域特征的方式，对扫描图像进行识别。其中，文字区域特征包括扫描图像的纹理、色差、光线、前后色差对比特征等。
而且，在提取文字区域特征的过程中，可以扫描图像的轮廓曲度最大或者轮廓特征的地方抽取关键的特征信息，以便判断扫描图像是否存在反光区域或曲面区域。
进一步的，可以通过收集用户确认的有反光的照片作为参照物，并通过提取扫描图像的关键特征信息，并将提取的关键特征信息与参照物同处关键特征信息进行比对。其中，标准化关键特征信息分别形成参照物特征向量a和待定照片特征向量b，计算关键特征信息向量a与b的相似度；例如，相似度可以取为a和b的二范数，如果相似度在一定阈值范围内则判断扫描图像存在反光区域。
在确定扫描图像存在反光区域的情况下，则可以通过调整摄像头的拍摄参数，以减少或者消除文档的反光，以便采集对应的图像。
步骤102、根据调整后的所述拍摄参数，采集第二图像。
该步骤中，第二图像可以与反光区域关联的图像，即通过调整拍摄参数的方式，减少或消除反光区域对应的特征信息的反光，以便采集对应的第二图像。
比如，第一图像的反光区域对应的图像特征为特征A，则可以通过调整拍摄参数的方式减少或者消除目标对象的特征A的反光，以使采集到的第二 图像中的特征A对应的图像区域没有反光。
步骤103、对目标图像进行识别，得到对应的识别结果。
该步骤中，目标图像包括第二图像，或者，目标图像根据第一图像和第二图像得到。
其中，针对目标图像包括第二图像的情况下，即第二图像可以是目标对象的整体扫描图像，且第二图像中未存在反光区域，因此可以通过对第二图像进行识别，以得到目标对象对应的识别结果。
进一步的，针对目标图像包括第一图像和第二图像的情况下，即第二图像仅是目标对象的局部扫描图像，甚至第二图像可以仅是第一图像中与反光区域关联的图像特征对应的图像；则可以分别识别第一图像的内容，以及第二图像的内容，并基于识别到的内容进行合成处理，以得到目标对象对应的识别结果。
另外，针对目标对象根据第一图像和第二图像得到的情况，可以先将第一图像和第二图像进行融合，以得到目标图像，然后对目标图像进行识别，以得到对应的识别结果。
这样在采集到的第一图像中包括反光区域的情况下，可以通过调整拍摄参数，消除或者减少反光区域对应的特征信息的反光，以便采集对应的第二图像，进而降低图像识别过程中反光区域对识别结果的影响，提升识别结果的准确度。
需要说明的是，目标对象还可以包括其他扫描图像。
可选的，其他扫描图像中包括存在曲面区域的扫描图像，则可以对包括曲面区域的扫描图像进行平铺处理，以便对包括曲面区域的扫描图像进行识别；或者，其他扫描图像中包括存在模糊区域的扫描图像，则可以对包括模糊区域的扫描图像进行去模糊化处理，以便对包括模糊区域的扫描图像进行识别。这样可以提升其他扫描图像的识别结果的准确度。
这样，在获取目标对象的识别结果的过程中，可以将目标图像对应的识别结果与目标对象的其他扫描图像对应的识别结果进行合并处理，以便得到 目标对象的识别结果。
其中，在目标图像对应的识别结果与目标对象的其他扫描图像对应的识别结果进行合并处理中，可以基于图像间的共有区域的识别内容作为合并的衔接位置，以提升合并处理的准确度，进而提升识别结果的准确度。
可选的，所述目标图像包括所述第一图像和所述第二图像，所述对目标图像进行识别，得到对应的识别结果，包括：
对所述第一图像进行识别，得到第一识别结果；
对所述第二图像进行识别，得到第二识别结果；
基于所述第一识别结果和所述第二识别结果确定所述第一图像和所述第二图像的公共区域的识别内容；
基于所述公共区域的识别内容，将所述第一识别结果和所述第二识别结果进行合并处理，得到所述目标图像对应的识别结果。
本实施方式中，可以将公共区域的识别内容，作为第一识别结果和第二识别结果的衔接内容，以提升合并处理的准确度，进而提升识别结果的准确度。
比如，在目标对象为文档的情况下，在对第一图像进行识别的过程中，可以识别第一图像中的字符信息，还可以记录每个字符的位置信息，以得到第一识别结果；相应的，也可以识别第二图像中的字符信息，以及记录每个字符的位置信息，以得到第二识别结果。
进一步可选的，所述基于所述第一识别结果和所述第二识别结果确定所述第一图像和所述第二图像的公共区域的识别内容，包括：获取所述第一识别结果中第一字符的字符信息和位置信息；获取所述第二识别结果中第二字符的字符信息和位置信息；在所述第一字符的字符信息和位置信息与所述第二字符的字符信息和位置信息均相同的情况下，将所述第一字符或者所述第二字符作为所述第一图像和所述第二图像的公共区域的识别内容。
一个实施例中，可以通过计算字符的行数和坐标信息，确定字符的位置信息。
另一个实施例中，可以记录每个字符上下左右四个方形分布的字符信息，每个方向可以记录一个或者多个字符，具体数量可以根据实际需求进行调整，以尽量保证每个字符周围相邻的字符分布的唯一性，从而保证字符的位置信息的准确性。
这样可以提升第一图像和第二图像的公共区域的识别内容的准确度，进而提升合并处理的准确度。
可选的，所述基于所述公共区域的识别内容，将所述第一识别结果和所述第二识别结果进行合并处理，得到所述目标图像对应的识别结果，包括：
基于所述公共区域的识别内容，将所述第一识别结果和所述第二识别结果进行合并处理，得到合并识别结果；
获取与所述第一识别结果关联的第一内容，以及与所述第二识别结果关联的第二内容；
基于所述第一内容和所述第二内容，对所述合并识别结果进行校验，得到所述目标图像对应的识别结果。
本实施方式中，对于识别到的识别结果，可以通过在线搜索功能，获取与识别结果关联的内容，即获取与识别结果相似度高的内容，并将其对合并识别结果进行校验，避免识别结果的缺少，以进一步提升识别结果的准确度。
比如，在识别的结果有明显的错误，或者因为拍摄的瑕疵问题导致文档部分内容缺失没法识别的情况下，可以将检索获取到的第一内容、第二内容，对合并识别结果进行补充或替换，提升合并识别结果的完整性。
可选的，所述根据调整后的所述拍摄参数，采集第二图像之后，所述对目标图像进行识别，得到对应的识别结果之前，所述方法还包括：
在所述第二图像中包括曲面区域的情况下，对所述第二图像进行平铺处理；
其中，所述目标图像包括平铺处理后的所述第二图像，或者，所述目标图像根据所述第一图像和平铺处理后的所述第二图像得到。
本实施方式中，针对第二图像存在曲面区域的情况下，可以对第二图像 进行平铺处理，以降低曲面区域对第二图像的识别结果的影响。
在进行平铺处理的过程中，可以通过计算曲面区域的曲面特征，并在平铺过程中保持对应信息变换过去，以便得到平铺处理后的图像特征。
另外，在第二图像中还包括模糊区域的情况下，还可以对第二图像中的模糊区域进行去模糊化处理，以降低模糊区域对识别结果的影响。
其中，图像模糊一般有两种情况，一种是图像本身由于拍摄原因导致模糊，另一种是图像放大后比较模糊。本申请中，模糊区域的成因主要是由于拍摄原因导致的模糊；针对由于拍摄原因形成的模糊区域，可以通过平滑和强化的方式进行去模糊化处理。
在本申请的一实施方式中，针对目标对象为曲面的情况，用户可以选择拍摄策略，以降低曲面对目标对象的识别结果的影响。其中，下述实施方式中，目标对象为文档。
如图2a所示，在对包括曲面的目标对象21的识别过程中，可以选择拍摄角度的顺序，从左至右采集目标对象的扫描图像；比如，可以先采集目标对象的左侧部分的内容，并得到第一扫描图像22，如图2b所示；然后采集目标对象的右侧部分的内容，并得到第二扫描图像23，如图2c所示。
然后，可以分别对第一扫描图像22和第二扫描图像23进行识别，并提取文字信息；在识别提取文字信息的过程中，若是第一扫描图像22和第二扫描图像23中的任一个存在反光区域的情况下，则执行步骤101至103，以消除反光区域对识别结果的影响。
在本申请的另一实施方式中，可以对目标对象的某个部位进行拍摄识别，或者将目标对象按照区域位置自动划分为多个对象，并对每个对象单独进行判断识别。而且，对于采集到的目标对象的扫描图像，可以通过对扫描图像进行识别提取，并将扫描图像中的清晰区域识别出来，对于不清晰的区域进行标记。
针对识别到的清晰区域的识别信息可以先存进行存储；对不清晰的区域进行标记并编号；然后，对不清晰的区域进行重新拍摄，以便获取其对应的 清晰的图像；在重新拍摄的过程中，可以基于用户的输入操作选取拍摄区域，也可以基于标记编号自动选取拍摄区域。
其中，若不清晰的区域为反光区域，则对反光区域对应的图像特征进行重新拍摄，并拍摄没有反光的图像；若不清晰的区域为曲面区域，则对曲面区域进行平铺处理，以降低曲面区域对识别结果的影响；若不清晰的区域为模糊区域，则可以对模糊区域进行去模糊化处理，以降低模糊区域对识别结果的影响。
另外，在获取到不清晰区域的清晰图像后，通过识别其内容，并可以基于其对应的标记编号与之前存储的清晰区域进行合并拼接处理，以获得目标对象的识别结果，达到提升识别结果的准确度的目的。
在本申请的又一实施方式中，在第一图像中存在反光区域的情况下，可以通过调整摄像头的拍摄参数，比如设置不同的光圈、焦点等参数，并可以拍摄多张图像存储起来，尽量使每处文字区域至少都有一张没反光的图像，以获取没有反光的第二图像。
而且，如果对拍摄的图像的去反光处理的效果不满意，还可以重新拍摄，直到获取到用户满意的去反光的图像。
本申请实施例的拍摄方法，通过在采集到的第一图像中包括反光区域的情况下，调整摄像头的拍摄参数，所述拍摄参数包括光圈、焦点中的至少一项；根据调整后的所述拍摄参数，采集第二图像；对目标图像进行识别，得到对应的识别结果；其中，所述目标图像包括第二图像，或者，所述目标图像根据所述第一图像和所述第二图像得到。这样在采集到的第一图像中包括反光区域的情况下，可以通过调整拍摄参数，消除或者减少反光区域对应的特征信息的反光，以便采集对应的第二图像，进而降低图像识别过程中反光区域对识别结果的影响，提升识别结果的准确度。
需要说明的是，本申请实施例提供的识别方法，执行主体可以为识别装置，或者该识别装置中的用于执行识别方法的控制模块。本申请实施例中以识别装置执行识别方法为例，说明本申请实施例提供的识别装置。
参见图3，图3是本申请一实施例提供的识别装置的结构图，如图3所示，该识别装置300包括：
调整模块301，用于在采集到的第一图像中包括反光区域的情况下，调整摄像头的拍摄参数，所述拍摄参数包括光圈、焦点中的至少一项；
采集模块302，用于根据调整后的所述拍摄参数，采集第二图像；
识别模块303，用于对目标图像进行识别，得到对应的识别结果；
其中，所述目标图像包括所述第二图像，或者，所述目标图像根据所述第一图像和所述第二图像得到。
可选的，所述目标图像包括所述第一图像和所述第二图像，所述识别模块303包括：
第一识别单元，用于对所述第一图像进行识别，得到第一识别结果；
第二识别单元，用于对所述第二图像进行识别，得到第二识别结果；
确定单元，用于基于所述第一识别结果和所述第二识别结果确定所述第一图像和所述第二图像的公共区域的识别内容；
合并单元，用于基于所述公共区域的识别内容，将所述第一识别结果和所述第二识别结果进行合并处理，得到所述目标图像对应的识别结果。
可选的，所述确定单元包括：
第一获取子单元，用于获取所述第一识别结果中第一字符的字符信息和位置信息；
第二获取子单元，用于获取所述第二识别结果中第二字符的字符信息和位置信息；
确定子单元，用于在所述第一字符的字符信息和位置信息与所述第二字符的字符信息和位置信息均相同的情况下，将所述第一字符或者所述第二字符作为所述第一图像和所述第二图像的公共区域的识别内容。
可选的，所述合并单元包括：
合并子单元，用于基于所述公共区域的识别内容，将所述第一识别结果和所述第二识别结果进行合并处理，得到合并识别结果；
第三获取子单元，用于获取与所述第一识别结果关联的第一内容，以及与所述第二识别结果关联的第二内容；
校验子单元，用于基于所述第一内容和所述第二内容，对所述合并识别结果进行校验，得到所述目标图像对应的识别结果。
可选的，所述识别装置300还包括：
平铺模块，用于在所述第二图像中包括曲面区域的情况下，对所述第二图像进行平铺处理；
其中，所述目标图像包括平铺处理后的所述第二图像，或者，所述目标图像根据所述第一图像和平铺处理后的所述第二图像得到。
本申请实施例中的识别装置可以是装置，也可以是终端中的部件、集成电路、或芯片。该装置可以是移动电子设备，也可以为非移动电子设备。示例性的，移动电子设备可以为手机、平板电脑、笔记本电脑、掌上电脑、车载电子设备、可穿戴设备、超级移动个人计算机(ultra-mobile personal computer，UMPC)、上网本或者个人数字助理(personal digital assistant，PDA)等，非移动电子设备可以为网络附属存储器(Network Attached Storage，NAS)、个人计算机(personal computer，PC)、电视机(television，TV)、柜员机或者自助机等，本申请实施例不作具体限定。
本申请实施例中的识别装置可以为具有操作***的装置。该操作***可以为安卓(Android)操作***，可以为ios操作***，还可以为其他可能的操作***，本申请实施例不作具体限定。
本申请实施例提供的识别装置能够实现图1的方法实施例实现的各个过程，为避免重复，这里不再赘述。
可选的，如图4所示，本申请实施例还提供一种电子设备400，包括处理器401，存储器402，存储在存储器402上并可在所述处理器401上运行的程序或指令，该程序或指令被处理器401执行时实现上述识别方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
需要说明的是，本申请实施例中的电子设备包括上述所述的移动电子设 备和非移动电子设备。
参见图5，图5是本申请一实施例提供的电子设备的结构图，如图5所示，该电子设备500包括但不限于：射频单元501、网络模块502、音频输出单元503、输入单元504、传感器505、显示单元506、用户输入单元507、接口单元508、存储器509、以及处理器510等部件。
本领域技术人员可以理解，电子设备500还可以包括给各个部件供电的电源(比如电池)，电源可以通过电源管理***与处理器510逻辑相连，从而通过电源管理***实现管理充电、放电、以及功耗管理等功能。图 5中示出的电子设备结构并不构成对电子设备的限定，电子设备可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置，在此不再赘述。
其中，处理器510，用于在采集到的第一图像中包括反光区域的情况下，调整摄像头的拍摄参数，所述拍摄参数包括光圈、焦点中的至少一项；输入单元504，用于根据调整后的所述拍摄参数，采集第二图像；处理器510，用于对目标图像进行识别，得到对应的识别结果；其中，所述目标图像包括所述第二图像，或者，所述目标图像根据所述第一图像和所述第二图像得到。
可选的，所述目标图像包括所述第一图像和所述第二图像，处理器510，用于对所述第一图像进行识别，得到第一识别结果；处理器510，用于对所述第二图像进行识别，得到第二识别结果；处理器510，用于基于所述第一识别结果和所述第二识别结果确定所述第一图像和所述第二图像的公共区域的识别内容；处理器510，用于基于所述公共区域的识别内容，将所述第一识别结果和所述第二识别结果进行合并处理，得到所述目标图像对应的识别结果。
可选的，处理器510，用于获取所述第一识别结果中第一字符的字符信息和位置信息；处理器510，用于获取所述第二识别结果中第二字符的字符信息和位置信息；处理器510，用于在所述第一字符的字符信息和位置信息与所述第二字符的字符信息和位置信息均相同的情况下，将所述第一字符或者所述第二字符作为所述第一图像和所述第二图像的公共区域的识别内容。
可选的，处理器510，用于基于所述公共区域的识别内容，将所述第一识别结果和所述第二识别结果进行合并处理，得到合并识别结果；处理器510，用于获取与所述第一识别结果关联的第一内容，以及与所述第二识别结果关联的第二内容；处理器510，用于基于所述第一内容和所述第二内容，对所述合并识别结果进行校验，得到所述目标图像对应的识别结果。
可选的，处理器510，用于在所述第二图像中包括曲面区域的情况下，对所述第二图像进行平铺处理；其中，所述目标图像包括平铺处理后的所述第二图像，或者，所述目标图像根据所述第一图像和平铺处理后的所述第二图像得到。
应理解的是，本申请实施例中，输入单元504可以包括图形处理器(Graphics Processing Unit，GPU)5041和麦克风5042，图形处理器5041对在视频捕获模式或图像捕获模式中由图像捕获装置(如摄像头)获得的静态图片或视频的图像数据进行处理。显示单元506可包括显示面板5061，可以采用液晶显示器、有机发光二极管等形式来配置显示面板5061。用户输入单元507包括触控面板5071以及其他输入设备5072。触控面板5071，也称为触摸屏。触控面板5071可包括触摸检测装置和触摸控制器两个部分。其他输入设备5072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆，在此不再赘述。存储器509可用于存储软件程序以及各种数据，包括但不限于应用程序和操作***。处理器510可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作***、用户界面和应用程序等，调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器510中。
本申请实施例还提供一种可读存储介质，所述可读存储介质上存储有程序或指令，该程序或指令被处理器执行时实现上述识别方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
其中，所述处理器为上述实施例中所述的电子设备中的处理器。所述可读存储介质，包括计算机可读存储介质，如计算机只读存储器(Read-Only  Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等。
本申请实施例另提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现上述识别方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
应理解，本申请实施例提到的芯片还可以称为***级芯片、***芯片、芯片***或片上***芯片等。
本申请实施例提供了一种计算机程序产品，所述程序产品被存储在非易失的存储介质中，所述程序产品被至少一个处理器执行以实现上述方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
本申请实施例提供了一种通信设备，被配置为执行如上述方法各个实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外，需要指出的是，本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能，还可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能，例如，可以按不同于所描述的次序来执行所描述的方法，并且还可以添加、省去、或组合各种步骤。另外，参照某些示例所描述的特征可在其他示例中被组合。
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。基于这样的理解，本申请的 技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
上面结合附图对本申请的实施例进行了描述，但是本申请并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本申请的启示下，在不脱离本申请宗旨和权利要求所保护的范围情况下，还可做出很多形式，均属于本申请的保护之内。

Claims (15)

  1. 一种识别方法，包括：
    在采集到的第一图像中包括反光区域的情况下，调整摄像头的拍摄参数，所述拍摄参数包括光圈、焦点中的至少一项；
    根据调整后的所述拍摄参数，采集第二图像；
    对目标图像进行识别，得到对应的识别结果；
    其中，所述目标图像包括所述第二图像，或者，所述目标图像根据所述第一图像和所述第二图像得到。
  2. 根据权利要求1所述的方法，其中，所述目标图像包括所述第一图像和所述第二图像，所述对目标图像进行识别，得到对应的识别结果，包括：
    对所述第一图像进行识别，得到第一识别结果；
    对所述第二图像进行识别，得到第二识别结果；
    基于所述第一识别结果和所述第二识别结果确定所述第一图像和所述第二图像的公共区域的识别内容；
    基于所述公共区域的识别内容，将所述第一识别结果和所述第二识别结果进行合并处理，得到所述目标图像对应的识别结果。
  3. 根据权利要求2所述的方法，其中，所述基于所述第一识别结果和所述第二识别结果确定所述第一图像和所述第二图像的公共区域的识别内容，包括：
    获取所述第一识别结果中第一字符的字符信息和位置信息；
    获取所述第二识别结果中第二字符的字符信息和位置信息；
    在所述第一字符的字符信息和位置信息与所述第二字符的字符信息和位置信息均相同的情况下，将所述第一字符或者所述第二字符作为所述第一图像和所述第二图像的公共区域的识别内容。
  4. 根据权利要求2所述的方法，其中，所述基于所述公共区域的识别内容，将所述第一识别结果和所述第二识别结果进行合并处理，得到所述目标图像对应的识别结果，包括：
    基于所述公共区域的识别内容，将所述第一识别结果和所述第二识别结果进行合并处理，得到合并识别结果；
    获取与所述第一识别结果关联的第一内容，以及与所述第二识别结果关联的第二内容；
    基于所述第一内容和所述第二内容，对所述合并识别结果进行校验，得到所述目标图像对应的识别结果。
  5. 根据权利要求1所述的方法，其中，所述根据调整后的所述拍摄参数，采集第二图像之后，所述对目标图像进行识别，得到对应的识别结果之前，所述方法还包括：
    在所述第二图像中包括曲面区域的情况下，对所述第二图像进行平铺处理；
    其中，所述目标图像包括平铺处理后的所述第二图像，或者，所述目标图像根据所述第一图像和平铺处理后的所述第二图像得到。
  6. 一种识别装置，包括：
    调整模块，用于在采集到的第一图像中包括反光区域的情况下，调整摄像头的拍摄参数，所述拍摄参数包括光圈、焦点中的至少一项；
    采集模块，用于根据调整后的所述拍摄参数，采集第二图像；
    识别模块，用于对目标图像进行识别，得到对应的识别结果；
    其中，所述目标图像包括所述第二图像，或者，所述目标图像根据所述第一图像和所述第二图像得到。
  7. 根据权利要求6所述的识别装置，其中，所述目标图像包括所述第一图像和所述第二图像，所述识别模块包括：
    第一识别单元，用于对所述第一图像进行识别，得到第一识别结果；
    第二识别单元，用于对所述第二图像进行识别，得到第二识别结果；
    确定单元，用于基于所述第一识别结果和所述第二识别结果确定所述第一图像和所述第二图像的公共区域的识别内容；
    合并单元，用于基于所述公共区域的识别内容，将所述第一识别结果和 所述第二识别结果进行合并处理，得到所述目标图像对应的识别结果。
  8. 根据权利要求7所述的识别装置，其中，所述确定单元包括：
    第一获取子单元，用于获取所述第一识别结果中第一字符的字符信息和位置信息；
    第二获取子单元，用于获取所述第二识别结果中第二字符的字符信息和位置信息；
    确定子单元，用于在所述第一字符的字符信息和位置信息与所述第二字符的字符信息和位置信息均相同的情况下，将所述第一字符或者所述第二字符作为所述第一图像和所述第二图像的公共区域的识别内容。
  9. 根据权利要求7所述的识别装置，其中，所述合并单元包括：
    合并子单元，用于基于所述公共区域的识别内容，将所述第一识别结果和所述第二识别结果进行合并处理，得到合并识别结果；
    第三获取子单元，用于获取与所述第一识别结果关联的第一内容，以及与所述第二识别结果关联的第二内容；
    校验子单元，用于基于所述第一内容和所述第二内容，对所述合并识别结果进行校验，得到所述目标图像对应的识别结果。
  10. 根据权利要求6所述的识别装置，其中，所述识别装置还包括：
    平铺模块，用于在所述第二图像中包括曲面区域的情况下，对所述第二图像进行平铺处理；
    其中，所述目标图像包括平铺处理后的所述第二图像，或者，所述目标图像根据所述第一图像和平铺处理后的所述第二图像得到。
  11. 一种电子设备，包括处理器，存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如权利要求1-5任一项所述的识别方法的步骤。
  12. 一种可读存储介质，所述可读存储介质上存储程序或指令，所述程序或指令被处理器执行时实现如权利要求1-5任一项所述的识别方法的步骤。
  13. 一种芯片，包括处理器和通信接口，所述通信接口和所述处理器耦 合，所述处理器用于运行程序或指令，实现如权利要求1至5中任一项所述的方法的步骤。
  14. 一种计算机程序产品，所述程序产品被存储在非易失的存储介质中，所述程序产品被至少一个处理器执行以实现如权利要求1至5中任一项所述的方法的步骤。
  15. 一种通信设备，被配置为执行如权利要求1至5中任一项所述的方法的步骤。
PCT/CN2021/132368 2020-11-27 2021-11-23 识别方法、装置及电子设备 WO2022111461A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US18/203,049 US20230306765A1 (en) 2020-11-27 2023-05-29 Recognition method and apparatus, and electronic device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011361267.5 2020-11-27
CN202011361267.5A CN112532884B (zh) 2020-11-27 2020-11-27 识别方法、装置及电子设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/203,049 Continuation US20230306765A1 (en) 2020-11-27 2023-05-29 Recognition method and apparatus, and electronic device

Publications (1)

Publication Number Publication Date
WO2022111461A1 true WO2022111461A1 (zh) 2022-06-02

Family

ID=74994215

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/132368 WO2022111461A1 (zh) 2020-11-27 2021-11-23 识别方法、装置及电子设备

Country Status (3)

Country Link
US (1) US20230306765A1 (zh)
CN (1) CN112532884B (zh)
WO (1) WO2022111461A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112532884B (zh) * 2020-11-27 2022-10-14 维沃移动通信有限公司 识别方法、装置及电子设备
CN113194253B (zh) * 2021-04-28 2023-04-28 维沃移动通信有限公司 去除图像反光的拍摄方法、装置和电子设备

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050088460A1 (en) * 2003-09-02 2005-04-28 Makoto Ouchi Association of image data with information that relates to variation at the time of photograhy, and utilization of the information associated with the image data
US20100155485A1 (en) * 2008-12-18 2010-06-24 Symbol Technologies, Inc. Two position zoom lens assembly for an imaging-based bar code reader
CN101882308A (zh) * 2010-07-02 2010-11-10 上海交通大学 提高图像拼接精度和稳定性的方法
CN105404838A (zh) * 2014-09-10 2016-03-16 霍尼韦尔国际公司 可变景深条形码扫描仪
CN108399540A (zh) * 2018-01-19 2018-08-14 广东小天才科技有限公司 基于移动终端的扫码支付方法、装置、终端及存储介质
CN108629220A (zh) * 2018-03-23 2018-10-09 阿里巴巴集团控股有限公司 一种二维码识读方法、装置及设备
CN108763998A (zh) * 2018-04-17 2018-11-06 维沃移动通信有限公司 条形码识别方法以及终端设备
CN109257540A (zh) * 2018-11-05 2019-01-22 浙江舜宇光学有限公司 多摄镜头组的摄影校正方法及摄影装置
CN110008943A (zh) * 2019-02-11 2019-07-12 阿里巴巴集团控股有限公司 一种图像处理方法及装置、一种计算设备及存储介质
CN111681160A (zh) * 2020-05-28 2020-09-18 深圳市无虚科技有限公司 曲面图像的还原方法、装置、设备及可读存储介质
CN112532884A (zh) * 2020-11-27 2021-03-19 维沃移动通信有限公司 识别方法、装置及电子设备

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005295313A (ja) * 2004-04-01 2005-10-20 Sharp Corp コード読取装置、電子機器、パラメータの調整方法及びパラメータ調整プログラム
CN102354363B (zh) * 2011-09-15 2014-04-16 西北工业大学 高反光柱面金属上的二维条码图像识别方法
CN105411523B (zh) * 2015-12-07 2020-04-10 温州医科大学眼视光器械有限公司 一种角膜图像处理方法
CN107292820A (zh) * 2017-05-11 2017-10-24 厦门中控智慧信息技术有限公司 图像拼接方法及装置
CN109598515B (zh) * 2018-11-29 2020-08-04 阿里巴巴集团控股有限公司 一种支付方法、支付装置及终端设备
CN111510623B (zh) * 2020-04-02 2022-02-15 维沃移动通信有限公司 拍摄方法及电子设备

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050088460A1 (en) * 2003-09-02 2005-04-28 Makoto Ouchi Association of image data with information that relates to variation at the time of photograhy, and utilization of the information associated with the image data
US20100155485A1 (en) * 2008-12-18 2010-06-24 Symbol Technologies, Inc. Two position zoom lens assembly for an imaging-based bar code reader
CN101882308A (zh) * 2010-07-02 2010-11-10 上海交通大学 提高图像拼接精度和稳定性的方法
CN105404838A (zh) * 2014-09-10 2016-03-16 霍尼韦尔国际公司 可变景深条形码扫描仪
CN108399540A (zh) * 2018-01-19 2018-08-14 广东小天才科技有限公司 基于移动终端的扫码支付方法、装置、终端及存储介质
CN108629220A (zh) * 2018-03-23 2018-10-09 阿里巴巴集团控股有限公司 一种二维码识读方法、装置及设备
CN108763998A (zh) * 2018-04-17 2018-11-06 维沃移动通信有限公司 条形码识别方法以及终端设备
CN109257540A (zh) * 2018-11-05 2019-01-22 浙江舜宇光学有限公司 多摄镜头组的摄影校正方法及摄影装置
CN110008943A (zh) * 2019-02-11 2019-07-12 阿里巴巴集团控股有限公司 一种图像处理方法及装置、一种计算设备及存储介质
CN111681160A (zh) * 2020-05-28 2020-09-18 深圳市无虚科技有限公司 曲面图像的还原方法、装置、设备及可读存储介质
CN112532884A (zh) * 2020-11-27 2021-03-19 维沃移动通信有限公司 识别方法、装置及电子设备

Also Published As

Publication number Publication date
CN112532884B (zh) 2022-10-14
CN112532884A (zh) 2021-03-19
US20230306765A1 (en) 2023-09-28

Similar Documents

Publication Publication Date Title
US10915998B2 (en) Image processing method and device
WO2022111461A1 (zh) 识别方法、装置及电子设备
JP5868816B2 (ja) 画像処理装置、画像処理方法、及びプログラム
CN109285136B (zh) 一种图像的多尺度融合方法、装置、存储介质及终端
WO2012075817A1 (zh) 一种文本图像的切边方法
CN108833785A (zh) 多视角图像的融合方法、装置、计算机设备和存储介质
WO2021136386A1 (zh) 数据处理方法、终端和服务器
EP3518522B1 (en) Image capturing method and device
CN111290684B (zh) 图像显示方法、图像显示装置及终端设备
CN110431563B (zh) 图像校正的方法和装置
CN110463177A (zh) 文档图像的校正方法及装置
CN105830091A (zh) 使用移动视频数据生成长文档的合成图像的***和方法
US20190005323A1 (en) Information processing apparatus for tracking processing
JP2017120503A (ja) 情報処理装置、情報処理装置の制御方法、及びプログラム
CN114494751A (zh) 证照信息识别方法、装置、设备及介质
JP2019012359A (ja) 情報処理装置、プログラム及び情報処理方法
US10999513B2 (en) Information processing apparatus having camera function, display control method thereof, and storage medium
US10373329B2 (en) Information processing apparatus, information processing method and storage medium for determining an image to be subjected to a character recognition processing
CN110610178A (zh) 图像识别方法、装置、终端及计算机可读存储介质
WO2022161324A1 (zh) 工作状态确定方法和装置
JP2012205089A (ja) 情報処理装置、情報処理方法、及び情報処理プログラム
CN114565777A (zh) 数据处理方法和装置
JP2005182098A (ja) 合成画像を生成・表示する装置及び方法
CN112150486A (zh) 图像处理方法及装置
Shao et al. Digital image aesthetic composition optimization based on perspective tilt correction

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21896962

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21896962

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 27/11/2023)