CN112818961A - Image feature identification method and device - Google Patents
Image feature identification method and device Download PDFInfo
- Publication number
- CN112818961A CN112818961A CN202110331011.8A CN202110331011A CN112818961A CN 112818961 A CN112818961 A CN 112818961A CN 202110331011 A CN202110331011 A CN 202110331011A CN 112818961 A CN112818961 A CN 112818961A
- Authority
- CN
- China
- Prior art keywords
- picture
- image
- recognition
- preset template
- acquiring
- 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
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004590 computer program Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 238000012795 verification Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
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
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/414—Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
-
- 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
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an image feature recognition method and device, wherein the method comprises the steps of obtaining a picture, recognizing the picture by adopting a preset template or a shape recognition model, and positioning after the picture is successfully recognized; adopt preset template to right the picture discerns, include: acquiring a matching area of the image of the preset template in the picture; and calculating the matching degree of the matching area, and determining that the identification is successful when the matching degree is greater than a preset threshold value. The invention can realize the recognition of characters or images on the pictures so as to position.
Description
Technical Field
The invention belongs to the technical field of image recognition, and particularly relates to an image feature recognition method and device.
Background
Image recognition, which refers to a technique for processing, analyzing and understanding images by a computer to recognize various different patterns of objects and objects, is a practical application of applying a deep learning algorithm. Image recognition technology at present is generally divided into face recognition and commodity recognition, and the face recognition is mainly applied to security inspection, identity verification and mobile payment; the commodity identification is mainly applied to the commodity circulation process, in particular to the field of unmanned retail such as unmanned goods shelves and intelligent retail cabinets.
In the related art, the image recognition mode has the problem that the positioning cannot be realized.
Disclosure of Invention
In view of the above, the present invention provides an image feature recognition method and apparatus to solve the problem that image recognition in the prior art cannot be located.
In order to achieve the purpose, the invention adopts the following technical scheme: an image feature recognition method, comprising:
acquiring a picture;
recognizing the picture by adopting a preset template or a shape recognition model, and positioning after successful recognition;
adopt preset template to right the picture discerns, include:
acquiring a matching area of the image of the preset template in the picture;
and calculating the matching degree of the matching area, and determining that the identification is successful when the matching degree is greater than a preset threshold value.
Further, the acquiring the picture includes:
acquiring a picture to be identified in a mode of shooting or screenshot by a camera of a mobile client;
and if the inclination angle of the characters on the picture to be recognized is larger than a preset threshold value, performing inclination correction on the picture to be recognized to obtain the picture.
Further, recognizing the picture by using a shape recognition model, including:
acquiring a sample picture, and setting the shape and the type of the sample picture to obtain a training set and a test data set;
training the neural network model according to the training set and the test data set until the neural network model converges to obtain a shape recognition model;
preprocessing the picture to obtain an image to be processed;
and inputting the image to be processed into the shape recognition model for calculation, and outputting a recognition result.
Further, the picture is preprocessed, which includes:
graying the picture to obtain a grayscale image;
compressing the gray level image to obtain a compressed image;
and converting the compressed image into a one-dimensional vector and normalizing.
Further, preprocessing the picture, further comprising:
and performing layout analysis on the picture, including:
segmenting all character blocks in the picture, and distinguishing text paragraphs, typesetting sequences, intra-domain attributes and the relation of each character block;
and when the picture contains the table area, performing table analysis processing on the table area independently.
Further, the recognizing the picture by adopting a preset template further comprises:
and calculating the recognition rate.
Further, the calculating the recognition rate includes:
storing the match values in a matrix; the matching degree value is used as the top left corner vertex of the matrix;
and calculating the correlation coefficient of the matrix and carrying out normalization processing.
An embodiment of the present application provides an image feature recognition apparatus, including:
the acquisition module is used for acquiring pictures;
the recognition module is used for recognizing the picture by adopting a preset template or a shape recognition model and positioning the picture after the recognition is successful;
adopt preset template to right the picture discerns, include:
acquiring a matching area of the image of the preset template in the picture;
and calculating the matching degree of the matching area, and determining that the identification is successful when the matching degree is greater than a preset threshold value.
The embodiment of the application provides computer equipment, which comprises a processor and a memory connected with the processor;
the memory is used for storing a computer program, and the computer program is used for executing the image feature identification method provided by any one of the above embodiments;
the processor is used to call and execute the computer program in the memory.
By adopting the technical scheme, the invention can achieve the following beneficial effects:
the invention provides an image feature identification method and device, wherein the method comprises the steps of obtaining a picture, identifying the picture by adopting a preset template or a shape identification model, and positioning after successful identification; adopt preset template to right the picture discerns, include: acquiring a matching area of the image of the preset template in the picture; and calculating the matching degree of the matching area, and determining that the identification is successful when the matching degree is greater than a preset threshold value. The invention can realize the recognition of characters or images on the pictures so as to position.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram illustrating steps of an image feature recognition method according to the present invention;
fig. 2 is a schematic structural diagram of an image feature recognition device according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
A specific image feature recognition method provided in the embodiments of the present application is described below with reference to the drawings.
As shown in fig. 1, an image feature identification method provided in an embodiment of the present application includes:
s101, acquiring a picture;
s102, recognizing the picture by adopting a preset template or a shape recognition model, and positioning after successful recognition;
adopt preset template to right the picture discerns, include:
acquiring a matching area of the image of the preset template in the picture;
and calculating the matching degree of the matching area, and determining that the identification is successful when the matching degree is greater than a preset threshold value.
Preferably, the acquiring the picture includes:
acquiring a picture to be identified in a mode of shooting or screenshot by a camera of a mobile client;
and if the inclination angle of the characters on the picture to be recognized is larger than a preset threshold value, performing inclination correction on the picture to be recognized to obtain the picture.
The method and the device acquire the image-text data to be identified, generally speaking, the image through a camera or a screenshot mode. The quality of the picture is a prerequisite for correct recognition by OCR. The tilt angle of the character is small when the image to be recognized is detected by preprocessing, and the deformation of the character image is small after the tilt correction. The definition of the image characters is also an important identification index. The higher the quality of the image, the higher the recognition accuracy of the characters. On the contrary, if the picture quality is low, image samples such as half characters and the like may be detected if other noise points such as the broken strokes of the characters and the like are too much. When characters are broken and strokes are adhered, some characteristics are lost, and when the characteristics are compared with the characteristic library, the characteristic distance is increased, and the recognition rate is reduced.
The working principle of the image feature identification method is as follows: according to the method and the device, the picture is firstly obtained, then the picture is identified by adopting the preset template or the shape identification model, if the characteristics on the picture can be identified, the identification is successful, and the characteristics are positioned. For example, a user wants to click the verification code, first identifies whether the verification code exists, if so, performs positioning, and clicks the verification code after positioning, so that the working efficiency can be improved, and the time can be saved. Specifically, the step of identifying the picture by adopting a preset template is to find a small area matched with the image of the given template in the whole image area. On the image to be detected, the matching degree of the template image and the overlapped sub-images is calculated from left to right and from top to bottom, and the larger the matching degree is, the higher the possibility that the template image and the overlapped sub-images are the same is.
In some embodiments, recognizing the picture using a shape recognition model includes:
acquiring a sample picture, and setting the shape and the type of the sample picture to obtain a training set and a test data set;
training the neural network model according to the training set and the test data set until the neural network model converges to obtain a shape recognition model;
preprocessing the picture to obtain an image to be processed;
and inputting the image to be processed into the shape recognition model for calculation, and outputting a recognition result.
Preferably, the preprocessing the picture includes:
graying the picture to obtain a grayscale image;
compressing the gray level image to obtain a compressed image;
and converting the compressed image into a one-dimensional vector and normalizing.
Specifically, the shape recognition model is obtained firstly, and the specific process is that a large number of sample pictures are collected, and the shape and the type of the pictures are calibrated to obtain a training set and a test data set. Defining a multilayer perceptron, defining a data layer, acquiring a classifier, defining a loss function and accuracy, defining an optimization function, then training a neural network model, evaluating a shape recognition model after training to ensure the performance of the shape recognition model, preprocessing a picture when using the shape recognition model after acquiring the shape recognition model, firstly carrying out graying, then compressing the image, then converting the image into a one-dimensional vector, and finally carrying out normalization processing on the one-dimensional vector. A predictor for prediction is created, which reads the trained model to predict data that has never been encountered.
Preferably, the method further comprises the following steps:
and performing layout analysis on the picture, including:
segmenting all character blocks in the picture, and distinguishing text paragraphs, typesetting sequences, intra-domain attributes and the relation of each character block;
and when the picture contains the table area, performing table analysis processing on the table area independently.
Specifically, each character image in the image is sorted out and submitted to recognition, and the process is called image preprocessing. Preprocessing refers to some preparatory work prior to character recognition, including image cleaning to remove apparent noise (interference) in the original image. Analyzing the layout of the picture, confirming the typesetting of the selected text domain, segmenting the text lines of the horizontal and vertical typesetting, separating the text and the image of each line, distinguishing punctuation marks, and the like. The work at this stage is very important, and the processing effect directly influences the accuracy rate of character recognition. Layout analysis is the overall analysis of text images, which is to sort out all text blocks in a document, and distinguish text paragraphs, the typesetting sequence, and the areas of images and tables. The domain boundaries (coordinates of the start point and the end point of the domain in the image), the attributes (horizontal and vertical arrangement modes) in the domain and the connection relation of each character block are identified as a data structure. The text area is directly identified, the table area is exclusively analyzed and identified, and the image area is compressed or simply stored. The line character segmentation is to segment a large-sized image into lines and then separate a single character from the image lines.
Word recognition is the core technology of OCR character recognition. The computer converts the figure and image of the character detected from the image text into characters. The need to recognize these characters requires presetting various characteristics of the characters, such as the structure of the characters, the strokes of the characters, etc., in a character recognition system. And the preset information can meet the requirement until a very high recognition rate is achieved. Then, the image is analyzed and identified by combining strokes, characteristic points, projection information, point region distribution and the like of the characters.
In some embodiments, the recognizing the picture by using a preset template further includes:
and calculating the recognition rate.
Preferably, the calculating the recognition rate includes:
storing the match values in a matrix; the matching degree value is used as the top left corner vertex of the matrix;
and calculating the correlation coefficient of the matrix and carrying out normalization processing.
Specifically, in the process of matching the image of the preset template with the source image of the picture, the result of comparing and calculating the image of the preset template and the image of the currently intercepted picture is stored in a matrix. The value of each position (x, y) in the matrix represents the calculation result after the calculation of the image and the template pixel which are intercepted by taking the point as the top left corner vertex, and a value of a 0-1 interval is obtained after the calculation of the correlation coefficient and the normalization processing, and the closer to 1, the higher the recognition rate is.
The accuracy of picture feature identification can be further improved by calculating the identification rate, and identification errors are avoided.
As shown in fig. 2, an embodiment of the present application provides an image feature recognition apparatus, including:
an obtaining module 201, configured to obtain a picture;
the recognition module 202 is configured to recognize the picture by using a preset template or a shape recognition model, and perform positioning after the recognition is successful;
adopt preset template to right the picture discerns, include:
acquiring a matching area of the image of the preset template in the picture;
and calculating the matching degree of the matching area, and determining that the identification is successful when the matching degree is greater than a preset threshold value.
The working principle of the image feature recognition device provided by the embodiment of the application is that the acquisition module 201 acquires a picture; the recognition module 202 recognizes the picture by using a preset template or a shape recognition model, and positions the picture after the recognition is successful; identifying the picture by adopting a preset template, wherein a matching area of the picture and an image of the preset template is obtained; and calculating the matching degree of the matching area, and determining that the identification is successful when the matching degree is greater than a preset threshold value.
The embodiment of the application provides computer equipment, which comprises a processor and a memory connected with the processor;
the memory is used for storing a computer program, and the computer program is used for executing the image feature identification method provided by any one of the above embodiments;
the processor is used to call and execute the computer program in the memory.
In summary, the present invention provides an image feature recognition method and apparatus, where the method includes obtaining an image, recognizing the image by using a preset template or a shape recognition model, and positioning after the recognition is successful; adopt preset template to right the picture discerns, include: acquiring a matching area of the image of the preset template in the picture; and calculating the matching degree of the matching area, and determining that the identification is successful when the matching degree is greater than a preset threshold value. The invention can realize the recognition of characters or images on the pictures so as to position.
It is to be understood that the embodiments of the method provided above correspond to the embodiments of the apparatus described above, and the corresponding specific contents may be referred to each other, which is not described herein again.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (9)
1. An image feature recognition method, comprising:
acquiring a picture;
recognizing the picture by adopting a preset template or a shape recognition model, and positioning after successful recognition;
adopt preset template to right the picture discerns, include:
acquiring a matching area of the image of the preset template in the picture;
and calculating the matching degree of the matching area, and determining that the identification is successful when the matching degree is greater than a preset threshold value.
2. The method of claim 1, wherein the obtaining the picture comprises:
acquiring a picture to be identified in a mode of shooting or screenshot by a camera of a mobile client;
and if the inclination angle of the characters on the picture to be recognized is larger than a preset threshold value, performing inclination correction on the picture to be recognized to obtain the picture.
3. The method of claim 1, wherein recognizing the picture using a shape recognition model comprises:
acquiring a sample picture, and setting the shape and the type of the sample picture to obtain a training set and a test data set;
training the neural network model according to the training set and the test data set until the neural network model converges to obtain a shape recognition model;
preprocessing the picture to obtain an image to be processed;
and inputting the image to be processed into the shape recognition model for calculation, and outputting a recognition result.
4. The method of claim 3, wherein pre-processing the picture comprises:
graying the picture to obtain a grayscale image;
compressing the gray level image to obtain a compressed image;
and converting the compressed image into a one-dimensional vector and normalizing.
5. The method of claim 4, wherein pre-processing the picture further comprises:
and performing layout analysis on the picture, including:
segmenting all character blocks in the picture, and distinguishing text paragraphs, typesetting sequences, intra-domain attributes and the relation of each character block;
and when the picture contains the table area, performing table analysis processing on the table area independently.
6. The method of claim 1, wherein the recognizing the picture by using a preset template further comprises:
and calculating the recognition rate.
7. The method of claim 6, wherein the calculating the recognition rate comprises:
storing the match values in a matrix; the matching degree value is used as the top left corner vertex of the matrix;
and calculating the correlation coefficient of the matrix and carrying out normalization processing.
8. An image feature recognition device, comprising:
the acquisition module is used for acquiring pictures;
the recognition module is used for recognizing the picture by adopting a preset template or a shape recognition model and positioning the picture after the recognition is successful;
adopt preset template to right the picture discerns, include:
acquiring a matching area of the image of the preset template in the picture;
and calculating the matching degree of the matching area, and determining that the identification is successful when the matching degree is greater than a preset threshold value.
9. A computer device comprising a processor, and a memory coupled to the processor;
the memory is used for storing a computer program for executing the image feature recognition method according to any one of claims 1 to 7;
the processor is used for calling and executing the computer program in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110331011.8A CN112818961A (en) | 2021-03-26 | 2021-03-26 | Image feature identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110331011.8A CN112818961A (en) | 2021-03-26 | 2021-03-26 | Image feature identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112818961A true CN112818961A (en) | 2021-05-18 |
Family
ID=75863586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110331011.8A Pending CN112818961A (en) | 2021-03-26 | 2021-03-26 | Image feature identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112818961A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846379A (en) * | 2018-07-03 | 2018-11-20 | 南京览笛信息科技有限公司 | Face list recognition methods, system, terminal device and storage medium |
| CN110008944A (en) * | 2019-02-20 | 2019-07-12 | 平安科技（深圳）有限公司 | OCR recognition methods and device, storage medium based on template matching |
| WO2019174130A1 (en) * | 2018-03-14 | 2019-09-19 | 平安科技（深圳）有限公司 | Bill recognition method, server, and computer readable storage medium |
| CN111444922A (en) * | 2020-03-27 | 2020-07-24 | Oppo广东移动通信有限公司 | Picture processing method and device, storage medium and electronic equipment |
-
2021
- 2021-03-26 CN CN202110331011.8A patent/CN112818961A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019174130A1 (en) * | 2018-03-14 | 2019-09-19 | 平安科技（深圳）有限公司 | Bill recognition method, server, and computer readable storage medium |
| CN108846379A (en) * | 2018-07-03 | 2018-11-20 | 南京览笛信息科技有限公司 | Face list recognition methods, system, terminal device and storage medium |
| CN110008944A (en) * | 2019-02-20 | 2019-07-12 | 平安科技（深圳）有限公司 | OCR recognition methods and device, storage medium based on template matching |
| CN111444922A (en) * | 2020-03-27 | 2020-07-24 | Oppo广东移动通信有限公司 | Picture processing method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10635946B2 (en) | Eyeglass positioning method, apparatus and storage medium | |
| CN110148130B (en) | Method and device for detecting part defects | |
| US20200210786A1 (en) | Computer-executed method and apparatus for assessing vehicle damage | |
| US7120318B2 (en) | Automatic document reading system for technical drawings | |
| CN111368682B (en) | Method and system for detecting and identifying station caption based on master RCNN | |
| US7831068B2 (en) | Image processing apparatus and method for detecting an object in an image with a determining step using combination of neighborhoods of a first and second region | |
| CN110738030A (en) | Table reconstruction method and device, electronic equipment and storage medium | |
| CN114359553B (en) | Signature positioning method and system based on Internet of things and storage medium | |
| TWI776176B (en) | Device and method for scoring hand work motion and storage medium | |
| JP2005148987A (en) | Object identifying method and device, program and recording medium | |
| CN114049499A (en) | Target object detection method, apparatus and storage medium for continuous contour | |
| CN112052702A (en) | Method and device for identifying two-dimensional code | |
| CN115984662A (en) | Multi-mode data pre-training and recognition method, device, equipment and medium | |
| JP2007025902A (en) | Image processor and image processing method | |
| CN113673528B (en) | Text processing method, text processing device, electronic equipment and readable storage medium | |
| CN107992872B (en) | Method for carrying out text recognition on picture and mobile terminal | |
| CN111652117B (en) | Method and medium for segmenting multiple document images | |
| CN111414889A (en) | Financial statement identification method and device based on character identification | |
| CN116071348A (en) | Workpiece surface detection method and related device based on visual detection | |
| CN112818961A (en) | Image feature identification method and device | |
| EP0632404B1 (en) | Pattern recognition by generating and using zonal features and anti-features | |
| CN113627442A (en) | Medical information input method, device, equipment and storage medium | |
| CN109637056B (en) | Artificial intelligence supermarket checkout system | |
| CN115221909A (en) | Two-dimensional code identification method, device and equipment and computer readable storage medium | |
| CN113361547A (en) | Signature identification method, device, equipment and readable 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 |