CN113591849A - File review method, device, equipment and storage medium based on signature identification - Google Patents
File review method, device, equipment and storage medium based on signature identification Download PDFInfo
- Publication number
- CN113591849A CN113591849A CN202110880541.8A CN202110880541A CN113591849A CN 113591849 A CN113591849 A CN 113591849A CN 202110880541 A CN202110880541 A CN 202110880541A CN 113591849 A CN113591849 A CN 113591849A
- Authority
- CN
- China
- Prior art keywords
- signature
- image
- target
- file
- target image
- 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 39
- 238000012552 review Methods 0.000 title claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 39
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims description 41
- 238000011156 evaluation Methods 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 16
- 238000012553 document review Methods 0.000 claims description 14
- 238000001514 detection method Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 6
- 238000003708 edge detection Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000010606 normalization Methods 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application provides a file review method, a device, equipment and a storage medium based on signature identification, wherein a target image comprising a signature is extracted from a file to be reviewed, the target image is subjected to algorithm processing to obtain signature characters in the signature, and a review result of the file to be reviewed is determined according to the matching degree of the signature characters and standard signature characters, so that the automatic review of the file to be reviewed is realized, the review efficiency of the file is improved, the cost is saved, and the error rate is reduced.
Description
Technical Field
The embodiment of the application relates to the technical field of image processing, in particular to a file review method, device, equipment and storage medium based on signature identification.
Background
The signature is used as a power symbol and a function mark of a state organ, an enterprise and public institution and a social group, and is one of contents which need to be mainly checked when a related organization carries out the work of reporting and approving. In the prior art, whether a signature exists in a document or not is judged in the process of manual approval of a newspaper, and the validity and the correctness of information in the signature are checked, such as the signature on a business license, company official seals in some documents and the like. Therefore, the problems of low approval efficiency and high cost exist in the prior art.
Disclosure of Invention
The embodiment of the application provides a file review method, a device, equipment and a storage medium based on signature identification, and aims to solve the problems of low approval efficiency and high cost in the prior art.
In a first aspect, an embodiment of the present application provides a file review method based on signature identification, including:
extracting a target image comprising a signature from a file to be evaluated;
performing algorithm processing on the target image to obtain signature characters included in the signature;
and determining the evaluation result of the file to be evaluated according to the matching degree of the signature characters and the standard signature characters.
Optionally, the performing algorithm processing on the target image to obtain signature characters included in the signature includes:
extracting color values of pixel points in the target image to obtain a color value matrix of the target image;
extracting a signature image in the target image based on the transformation processing of the color value matrix;
and performing character recognition on the signature image by adopting a character recognition algorithm to obtain the signature characters.
Optionally, the color value matrix is formed by RGB values of pixels in the target image, and extracting the signature image in the target image based on the transformation processing on the color value matrix includes:
converting the RGB values in the color value matrix into HSV values according to the conversion relation between the RGB values and the HSV values to obtain a target color value matrix;
and extracting a red area in the target image according to the target color value matrix to obtain the signature image.
Optionally, the extracting a red region in the target image according to the target color value matrix to obtain the signature image includes:
extracting target pixel points with red HSV values in the target color value matrix according to the value range of the red HSV;
determining whether the contour of a red area in the target image is circular or not according to the target pixel point;
and if so, extracting the red region from the target image to obtain the signature image.
Optionally, after the region corresponding to the target pixel point is extracted and the signature image is obtained, the method further includes:
and carrying out transparency processing on the signature image to obtain a standard signature image.
Optionally, the extracting a target image including a signature from the document to be evaluated includes:
and performing feature extraction, area identification and image cutting on the file to be evaluated by adopting a preset target detection model to obtain the target image.
Optionally, the determining, according to the matching degree between the signature characters and the standard signature characters, a review result of the file to be reviewed includes:
and if the matching degree is greater than the threshold value of the matching degree, allowing the file to be reviewed to pass the review.
In a second aspect, an embodiment of the present application provides a document review device based on signature identification, including:
the image extraction module is used for extracting a target image comprising a signature from a file to be evaluated;
the image processing module is used for carrying out algorithm processing on the target image to obtain signature characters included in the signature;
and the character matching module is used for determining the evaluation result of the file to be evaluated according to the matching degree of the signature characters and the standard signature characters.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the document review method based on signature identification according to the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the signature identification-based file review method as described in the first aspect above.
According to the file review method, the file review device, the file review equipment and the storage medium based on signature identification, the target image including the signature is extracted from the file to be reviewed, algorithm processing is carried out on the target image to obtain the signature characters included in the signature, and the review result of the file to be reviewed is determined according to the matching degree of the signature characters and the standard signature characters, so that automatic review of the file to be reviewed is realized, the review efficiency of the file is improved, the cost is saved, and the error rate is reduced.
Drawings
FIG. 1 is a schematic flowchart of a document review method based on signature identification according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a target detection model according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a document review device based on signature identification according to a second embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some of the structures related to the present application are shown in the drawings, not all of the structures.
The main ideas of the technical scheme are as follows: based on the problems of low efficiency, high cost, high error rate and the like in the prior art, the application provides a file evaluation scheme based on signature intelligent identification, which comprises the steps of inputting a file to be evaluated into a pre-trained target detection model, carrying out feature extraction, area identification and image cutting on the file to be evaluated by the target detection model to obtain a target image comprising a signature, carrying out a series of image processing such as hue-saturation-value (HSV) extraction, edge detection, Hough change, transparentization and the like on the target image to obtain a signature image, finally extracting character contents in the image by a character identification algorithm, comparing the identified character contents with standard information pre-stored in a system to determine evaluation results of the file to be evaluated, and realizing automatic evaluation of related files, the file review efficiency is greatly improved, the cost is saved, and the error rate is reduced.
Example one
Fig. 1 is a schematic flow chart of a document review method based on signature recognition according to an embodiment of the present application, where the method according to the present embodiment can be executed by a document review device based on signature recognition according to an embodiment of the present application, and the device can be implemented by software and/or hardware and can be integrated in an electronic device such as a server and an intelligent terminal. As shown in fig. 1, the document review method based on signature identification of the embodiment includes:
s101, extracting a target image comprising a signature from a file to be evaluated.
The document to be evaluated in this embodiment may be a document that needs to be signed and examined in various scenarios, such as an evaluation document, an administrative approval document, a qualification certification document, and the like.
The target image is an image extracted from the file to be evaluated and including a signature, and is obtained by intercepting a part including the signature in the file to be evaluated.
In this embodiment, a target detection model for identifying and extracting signatures in documents to be evaluated with different contents and formats may be trained in advance, and accordingly, in this step, the documents to be evaluated are input into the target detection model, signatures are identified by the target detection model, and a target image including the signatures is cut out.
In a possible implementation manner, fig. 2 is a schematic structural diagram of an object detection model provided in an embodiment of the present application, and as shown in fig. 2, the object detection model used in this embodiment includes a feature extraction module, a region identification module, and an image cropping module.
The feature extraction module is used for extracting features such as height, edge, color and texture of each part of the file to be evaluated, comparing the features with signature features obtained by pre-training and identifying a feature region with the highest probability of signature features. It can be understood that the size of the feature region may be determined by the model training phase, for example, in this embodiment, the document to be evaluated may be traversed by taking a certain length (e.g., 2mm) as a step length according to the maximum circumscribed rectangle of the signature as a unit to obtain the feature matrix corresponding to the features of each portion, and then the feature matrix of each portion is compared with the feature matrix of the signature features to identify the portion with the highest similarity to the feature matrix of the signature features as the feature region, and accordingly, the size of the feature region is the size of the maximum circumscribed rectangle of the signature.
And the region identification module is used for determining the region coordinates of the feature region positioned by the feature extraction module from the file to be evaluated. It should be noted that, in this embodiment, the region coordinates identified by the region identification module only need to indicate the feature region range, and do not need to identify the coordinates of all points in the entire feature region, for example, if the feature region is a rectangle, the region identification module only needs to identify the coordinates of four vertices of the feature region.
And the image cutting module is used for cutting the characteristic area from the file to be evaluated according to the area coordinate positioned by the area identification module, and the image of the cut characteristic area is the target image.
S102, performing algorithm processing on the target image to obtain signature characters included in the signature.
Signature text is the text content in the signature. Since the correctness of the signature is the key for document review, after S101, further, in this embodiment, the target image is processed by a pre-designed image processing algorithm, so as to obtain the signature included in the signature.
Because the target image may include other images in addition to the signature image, performing the algorithm processing on the target image in this step includes: extracting signature images and identifying signature characters. These two parts will be described separately below:
signature image extraction
In this embodiment, based on the color values of the pixels in the target image, the signature image is extracted from the target image. Specifically, color values of all pixel points in the target image are extracted firstly, a color value matrix of the target image is obtained, and then the signature image in the target image is extracted based on the transformation processing of the color value matrix.
Optionally, in this embodiment, the color value extracted from the target image is an RGB value of each pixel, and the color value matrix of the target image is obtained by combining the RGB values of each pixel. It can be understood that the RGB value of each pixel point is composed of an R value, a G value, and a B value, and can be expressed as an array such as (R, G, B), where the R value represents a color value of a pixel point R channel, the G value represents a color value of a pixel point G channel, and the B value represents a color value of a pixel point B channel.
Correspondingly, in this embodiment, based on the color value matrix, the signature image may be extracted by the following processing:
(1) HSV chrominance extraction
In this embodiment, the RGB values in the color value matrix are converted into HSV values according to the conversion relationship between the RGB values and the HSV values, so as to obtain a target color value matrix. For the convenience of distinguishing, a matrix formed by HSV values of pixel points in the target image is called a target color value matrix.
Similar to the RGB values, the HSV value of each pixel is also composed of an H value, an S value, and a V value, and can be represented by an array such as (H, S, V), where H represents the hue value of a pixel, S represents the saturation value of a pixel, and V represents the lightness value of a pixel. For the same pixel point, the RGB value can be converted into HSV value through the following conversion formula:
a. calculation of normalized color values:
this implementation is complete, carries out normalization processing to R value, G value and B value earlier, obtains the corresponding normalization colour value.
R′＝R/255 (1)
G′＝G/255 (2)
B′＝B/255 (3)
Cmax＝max(R′,G′,B′) (4)
Cmin＝min(R′,G′,B′) (5)
CΔ＝Cmax-Cmin (6)
Wherein R ' represents the normalized color value of the R channel, G ' represents the normalized color value of the G pass, B ' represents the normalized color value of the B pass, CmaxRepresenting the maximum normalized color value, CminRepresenting the maximum normalized color value, CΔThe color span value is normalized.
b. H value calculation:
in this example, according to CΔAnd CmaxAnd calculating the H value according to the value taking condition of the (1).
If CΔ0, then H is 0 °;
if CmaxR', the H value is calculated by the following formula:
if CmaxG', the H value is calculated by the following formula:
if CmaxB', the H value is calculated by the following formula:
c. and (3) calculating the S value:
in this example, according to CmaxWhether the value of (2) is 0 or not, and calculating the S value.
If CmaxWhen S is 0, S is 0;
if CmaxNot equal to 0, the value of S is calculated by the following formula:
d. and V value calculation:
in this embodiment, the V value is calculated according to the following formula:
V＝Cmax (11)
in this embodiment, based on the above calculation process, the target color value matrix is obtained by transforming the RGB values of the pixels in the color value matrix. Further, in this embodiment, according to the red HSV value range, a target pixel point of which the HSV value is red in the target color value matrix, that is, a pixel point of a red region on the target image, is extracted.
It can be understood that, if the color of the signature used in a certain scene is not red, in this embodiment, the HSV value range of red is replaced by the HSV value range of the color used for the corresponding signature, for example, blue, and the target pixel point is extracted according to the HSV value of each pixel point in the target color value matrix.
(2) Edge detection and Hough transform
In this embodiment, in order to ensure the accuracy of the finally extracted signature image, it is necessary to determine whether the red region is circular, if so, it may be determined that the identified red region is a signature, and if not, it may be determined that the identified red region is not a signature, which indicates that there is a problem in the identification process, such as interference or error, and need to be identified again or manually processed.
Therefore, in the step, based on the target pixel points extracted in the step (1), whether a red region in the target image is circular or not is determined through edge detection and Hough change, and if the red region is circular, the red region determined by the target pixel points is extracted to obtain the signature image.
The edge detection is used for positioning a target pixel point at the edge of a red area, and further, according to the Hough change principle, according to the coordinate of the target pixel point at the edge of the red area, whether the target pixel point at the edge of the red area can form a circle with (a, b) as the circle center and r as the radius is determined by solving the coordinate and the radius of the circle center, that is, whether all the target pixel points at the edge of the red area are on the same circle is determined, if yes, the outline of the red area in the target area is determined to be circular, and if not, the outline of the red area in the target area is not circular.
(3) Transparentizing treatment
After the contour of a red area in the target image is determined to be circular through edge detection and Hough change, all target pixel points are extracted from the target image, and then the signature image can be obtained. Because the signature image is only cut and extracted from the target image and does not meet the requirements of electronic signature service, the extracted signature image needs to be subjected to transparentization processing, and for the convenience of distinguishing, the signature image subjected to transparentization processing is called a standard signature image.
In a possible implementation manner, in this embodiment, the color values of the R channel (red channel) and the alpha channel of each target pixel are set to 255, the color values of the G channel and the B channel are set to 0, the color values of the R channel, the G channel, and the B channel of each pixel other than the target pixel are set to 255, and the value of the alpha channel is set to 0, so that the signature image is standardized to obtain a standard signature image without a background.
(II) signature character recognition
After the signature image is obtained, in this embodiment, in order to meet the requirement of review, the text content in the signature needs to be identified.
In this embodiment, the signature characters may be obtained by performing character recognition on the signature image by using an existing character recognition technology, such as an Optical Character Recognition (OCR) algorithm. The specific implementation process and principle can refer to the scheme in the prior art, and the scheme is not limited in the process.
S103, determining the evaluation result of the file to be evaluated according to the matching degree of the signature characters and the standard signature characters.
After the step S102, in this step, the extracted signature characters are compared with the standard signature characters stored in advance, and the matching degree between the characters and the standard signature characters is determined, if the matching degree meets the preset matching degree requirement, the document to be evaluated is allowed to pass the evaluation, otherwise, the document to be evaluated is not allowed to pass the evaluation.
Optionally, the matching degree requirement in this embodiment is greater than a matching degree threshold, and accordingly, if the calculated matching degree is greater than the matching degree threshold, the review of the file to be reviewed is passed, otherwise, the review of the file to be reviewed is not passed.
The standard signature characters are correct signature characters which the file to be evaluated should have, and are obtained by performing character recognition on the signatures in the standard file corresponding to the file to be evaluated in advance.
In this embodiment, the greater the matching degree, the higher the similarity between the signature and the standard signature. In order to ensure the credibility of the evaluation result, the matching degree threshold value should be not less than 90% as much as possible.
It is understood that different standard signature characters can be set in advance for different application scenarios. In addition, in this embodiment, not only the contents of the characters need to be compared, but also the formats, the typesetting, and the like of the characters need to be compared.
In the embodiment, the target image comprising the signature is extracted from the file to be evaluated, the algorithm processing is carried out on the target image to obtain the signature characters in the signature, and the evaluation result of the file to be evaluated is determined according to the matching degree of the signature characters and the standard signature characters, so that the automatic evaluation of the file to be evaluated is realized, the evaluation efficiency of the file is improved, the cost is saved, and the error rate is reduced.
Example two
Fig. 3 is a schematic structural diagram of a document review device based on signature identification according to a second embodiment of the present application, and as shown in fig. 3, the document review device 10 based on signature identification according to the present embodiment includes:
an image extraction module 11, an image processing module 12 and a character matching module 13.
The image extraction module 11 is used for extracting a target image comprising a signature from a file to be evaluated;
the image processing module 12 is configured to perform algorithm processing on the target image to obtain signature characters included in the signature;
and the character matching module 13 is used for determining the evaluation result of the file to be evaluated according to the matching degree of the signature characters and the standard signature characters.
Optionally, the image processing module 12 is specifically configured to:
extracting color values of pixel points in the target image to obtain a color value matrix of the target image;
extracting a signature image in the target image based on the transformation processing of the color value matrix;
and performing character recognition on the signature image by adopting a character recognition algorithm to obtain the signature characters.
Optionally, the color value matrix is formed by RGB values of pixels in the target image, and the image processing module 12 is specifically configured to:
converting the RGB values in the color value matrix into HSV values according to the conversion relation between the RGB values and the HSV values to obtain a target color value matrix;
and extracting a red area in the target image according to the target color value matrix to obtain the signature image.
Optionally, the image processing module 12 is specifically configured to:
extracting target pixel points with red HSV values in the target color value matrix according to the value range of the red HSV;
determining whether the contour of a red area in the target image is circular or not according to the target pixel point;
and if so, extracting the red region from the target image to obtain the signature image.
Optionally, the image processing module 12 is further configured to:
and carrying out transparency processing on the signature image to obtain a standard signature image.
Optionally, the image extraction module 11 is specifically configured to:
and performing feature extraction, area identification and image cutting on the file to be evaluated by adopting a preset target detection model to obtain the target image.
Optionally, the text matching module 13 is specifically configured to:
and if the matching degree is greater than the threshold value of the matching degree, allowing the file to be reviewed to pass the review.
The signature recognition-based file review device provided by the embodiment can execute the signature recognition-based file review method provided by the method embodiment, and has corresponding functional modules and beneficial effects of the execution method. The implementation principle and technical effect of this embodiment are similar to those of the above method embodiments, and are not described in detail here.
EXAMPLE III
Fig. 4 is a schematic structural diagram of an electronic device according to a third embodiment of the present application, as shown in fig. 4, the electronic device 20 includes a memory 21, a processor 22, and a computer program stored in the memory and executable on the processor; the number of the processors 22 of the electronic device 20 may be one or more, and one processor 22 is taken as an example in fig. 4; the processor 22 and the memory 21 in the electronic device 20 may be connected by a bus or other means, and fig. 4 illustrates the connection by the bus as an example.
The memory 21 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the image extraction module 11, the image processing module 12, and the text matching module 13 in the embodiment of the present application. The processor 22 executes various functional applications and data processing of the device/terminal/server by running software programs, instructions and modules stored in the memory 21, namely, implements the above-mentioned file review method based on signature recognition.
The memory 21 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 21 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 21 may further include memory located remotely from the processor 22, which may be connected to the device/terminal/server through a grid. Examples of such a mesh include, but are not limited to, the internet, an intranet, a local area network, a mobile communications network, and combinations thereof.
Example four
A fourth embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, the computer program, when executed by a computer processor, is configured to perform a document review method based on signature recognition, the method including:
extracting a target image comprising a signature from a file to be evaluated;
performing algorithm processing on the target image to obtain signature characters included in the signature;
and determining the evaluation result of the file to be evaluated according to the matching degree of the signature characters and the standard signature characters.
Of course, the computer program of the computer-readable storage medium provided in this embodiment of the present application is not limited to the method operations described above, and may also perform related operations in the signature identification-based document review method provided in any embodiment of the present application.
From the above description of the embodiments, it is obvious for those skilled in the art that the present application can be implemented by software and necessary general hardware, and certainly can be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a grid device) to execute the methods described in the embodiments of the present application.
It should be noted that, in the embodiment of the file review device based on signature identification, the included units and modules are only divided according to the functional logic, but are not limited to the above division as long as the corresponding functions can be realized; in addition, specific names of the functional units are only used for distinguishing one functional unit from another, and are not used for limiting the protection scope of the application.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present application and the technical principles employed. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the appended claims.
Claims (10)
1. A file review method based on signature identification is characterized by comprising the following steps:
extracting a target image comprising a signature from a file to be evaluated;
performing algorithm processing on the target image to obtain signature characters included in the signature;
and determining the evaluation result of the file to be evaluated according to the matching degree of the signature characters and the standard signature characters.
2. The method according to claim 1, wherein the performing algorithm processing on the target image to obtain signature text included in the signature comprises:
extracting color values of pixel points in the target image to obtain a color value matrix of the target image;
extracting a signature image in the target image based on the transformation processing of the color value matrix;
and performing character recognition on the signature image by adopting a character recognition algorithm to obtain the signature characters.
3. The method of claim 2, wherein the color value matrix is composed of RGB values of pixels in the target image, and the extracting the signature image from the target image based on the transformation processing of the color value matrix comprises:
converting the RGB values in the color value matrix into HSV values according to the conversion relation between the RGB values and the HSV values to obtain a target color value matrix;
and extracting a red area in the target image according to the target color value matrix to obtain the signature image.
4. The method of claim 3, wherein the extracting a red region in the target image according to the target color value matrix to obtain the signature image comprises:
extracting target pixel points with red HSV values in the target color value matrix according to the value range of the red HSV;
determining whether the contour of a red area in the target image is circular or not according to the target pixel point;
and if so, extracting the red region from the target image to obtain the signature image.
5. The method according to claim 4, wherein after the extracting of the region corresponding to the target pixel point obtains the signature image, the method further comprises:
and carrying out transparency processing on the signature image to obtain a standard signature image.
6. The method of claim 1, wherein extracting the target image including the signature from the document to be evaluated comprises:
and performing feature extraction, area identification and image cutting on the file to be evaluated by adopting a preset target detection model to obtain the target image.
7. The method of claim 1, wherein determining the review result of the document to be reviewed according to the matching degree of the signature characters and the standard signature characters comprises:
and if the matching degree is greater than the threshold value of the matching degree, allowing the file to be reviewed to pass the review.
8. A document review device based on signature identification, comprising:
the image extraction module is used for extracting a target image comprising a signature from a file to be evaluated;
the image processing module is used for carrying out algorithm processing on the target image to obtain signature characters included in the signature;
and the character matching module is used for determining the evaluation result of the file to be evaluated according to the matching degree of the signature characters and the standard signature characters.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the signature recognition based document review method as claimed in any one of claims 1-7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the signature identification-based file review method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110880541.8A CN113591849A (en) | 2021-08-02 | 2021-08-02 | File review method, device, equipment and storage medium based on signature identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110880541.8A CN113591849A (en) | 2021-08-02 | 2021-08-02 | File review method, device, equipment and storage medium based on signature identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113591849A true CN113591849A (en) | 2021-11-02 |
Family
ID=78253658
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110880541.8A Pending CN113591849A (en) | 2021-08-02 | 2021-08-02 | File review method, device, equipment and storage medium based on signature identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113591849A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114708592A (en) * | 2022-05-16 | 2022-07-05 | 北京万里红科技有限公司 | Seal security level judging method, device, equipment and computer readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944452A (en) * | 2017-12-12 | 2018-04-20 | 深圳市创业印章实业有限公司 | A kind of circular stamp character recognition method |
| CN110059722A (en) * | 2019-03-16 | 2019-07-26 | 平安城市建设科技(深圳)有限公司 | Checking method, device, equipment and the readable storage medium storing program for executing of seal image |
| CN112381081A (en) * | 2020-11-16 | 2021-02-19 | 深圳壹账通智能科技有限公司 | Official seal character automatic identification method and device, computer equipment and storage medium |
| CN113076795A (en) * | 2021-02-09 | 2021-07-06 | 江苏省联合征信有限公司 | Automatic auditing method for form protocol image with seal |
-
2021
- 2021-08-02 CN CN202110880541.8A patent/CN113591849A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944452A (en) * | 2017-12-12 | 2018-04-20 | 深圳市创业印章实业有限公司 | A kind of circular stamp character recognition method |
| CN110059722A (en) * | 2019-03-16 | 2019-07-26 | 平安城市建设科技(深圳)有限公司 | Checking method, device, equipment and the readable storage medium storing program for executing of seal image |
| CN112381081A (en) * | 2020-11-16 | 2021-02-19 | 深圳壹账通智能科技有限公司 | Official seal character automatic identification method and device, computer equipment and storage medium |
| CN113076795A (en) * | 2021-02-09 | 2021-07-06 | 江苏省联合征信有限公司 | Automatic auditing method for form protocol image with seal |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114708592A (en) * | 2022-05-16 | 2022-07-05 | 北京万里红科技有限公司 | Seal security level judging method, device, equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107944452B (en) | Character recognition method for circular seal | |
| US11164027B2 (en) | Deep learning based license plate identification method, device, equipment, and storage medium | |
| US11663817B2 (en) | Automated signature extraction and verification | |
| WO2019237549A1 (en) | Verification code recognition method and apparatus, computer device, and storage medium | |
| WO2022156178A1 (en) | Image target comparison method and apparatus, computer device and readable storage medium | |
| CN108830275B (en) | Method and device for identifying dot matrix characters and dot matrix numbers | |
| CN109635805B (en) | Image text positioning method and device and image text identification method and device | |
| CN110210297B (en) | Method for locating and extracting Chinese characters in customs clearance image | |
| CN110675940A (en) | Pathological image labeling method and device, computer equipment and storage medium | |
| CN112669515A (en) | Bill image recognition method and device, electronic equipment and storage medium | |
| CN112418180A (en) | Table data extraction method, device, equipment and computer storage medium | |
| CN112396047B (en) | Training sample generation method and device, computer equipment and storage medium | |
| US8300952B2 (en) | Electronic document comparison system and method | |
| CN112581344A (en) | Image processing method and device, computer equipment and storage medium | |
| CN112651953A (en) | Image similarity calculation method and device, computer equipment and storage medium | |
| CN111046754B (en) | Character recognition method, device and computer readable storage medium | |
| CN112232336A (en) | Certificate identification method, device, equipment and storage medium | |
| CN114581646A (en) | Text recognition method and device, electronic equipment and storage medium | |
| CN113591849A (en) | File review method, device, equipment and storage medium based on signature identification | |
| CN111462388A (en) | Bill inspection method and device, terminal equipment and storage medium | |
| CN111738979A (en) | Automatic certificate image quality inspection method and system | |
| US11176363B2 (en) | System and method of training a classifier for determining the category of a document | |
| Andreeva et al. | Comparison of scanned administrative document images | |
| CN115410191B (en) | Text image recognition method, device, equipment and storage medium | |
| CN111259894B (en) | Certificate information identification method and device and computer equipment |
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 |