CN111680694A - Method and device for filtering colored seal in character image - Google Patents
Method and device for filtering colored seal in character image Download PDFInfo
- Publication number
- CN111680694A CN111680694A CN202010470474.8A CN202010470474A CN111680694A CN 111680694 A CN111680694 A CN 111680694A CN 202010470474 A CN202010470474 A CN 202010470474A CN 111680694 A CN111680694 A CN 111680694A
- Authority
- CN
- China
- Prior art keywords
- colored
- character image
- matrix
- image
- processing
- 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
- 238000001914 filtration Methods 0.000 title claims abstract description 117
- 238000000034 method Methods 0.000 title claims abstract description 69
- 239000011159 matrix material Substances 0.000 claims abstract description 126
- 238000012545 processing Methods 0.000 claims abstract description 106
- 230000004927 fusion Effects 0.000 claims abstract description 49
- 239000003086 colorant Substances 0.000 claims abstract description 24
- 238000004590 computer program Methods 0.000 claims description 16
- 238000010606 normalization Methods 0.000 claims description 12
- 238000000926 separation method Methods 0.000 claims description 10
- 230000008030 elimination Effects 0.000 abstract description 9
- 238000003379 elimination reaction Methods 0.000 abstract description 9
- 238000012015 optical character recognition Methods 0.000 description 23
- 238000010586 diagram Methods 0.000 description 16
- 238000004422 calculation algorithm Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 13
- 238000004891 communication Methods 0.000 description 12
- 230000003044 adaptive effect Effects 0.000 description 5
- 238000007781 pre-processing Methods 0.000 description 5
- 239000000872 buffer Substances 0.000 description 4
- 238000003672 processing method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007499 fusion processing Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- ORFSSYGWXNGVFB-UHFFFAOYSA-N sodium 4-amino-6-[[4-[4-[(8-amino-1-hydroxy-5,7-disulfonaphthalen-2-yl)diazenyl]-3-methoxyphenyl]-2-methoxyphenyl]diazenyl]-5-hydroxynaphthalene-1,3-disulfonic acid Chemical compound COC1=C(C=CC(=C1)C2=CC(=C(C=C2)N=NC3=C(C4=C(C=C3)C(=CC(=C4N)S(=O)(=O)O)S(=O)(=O)O)O)OC)N=NC5=C(C6=C(C=C5)C(=CC(=C6N)S(=O)(=O)O)S(=O)(=O)O)O.[Na+] ORFSSYGWXNGVFB-UHFFFAOYSA-N 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/273—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion removing elements interfering with the pattern to be recognised
-
- 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
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Character Input (AREA)
Abstract
The embodiment of the application provides a method and a device for filtering a colored seal in a text image, wherein the method comprises the following steps: carrying out pixel superposition processing on binarization matrixes corresponding to three primary color channels of a target character image comprising a colored stamp to obtain a superposition fusion matrix of the target character image; and acquiring a standard pixel value matrix corresponding to the superposition fusion matrix, and performing binarization processing on the standard pixel value matrix to obtain a gray level character image with the colored seal filtered out so as to acquire an OCR character recognition result of the gray level character image. The method and the device can perform self-adaptive elimination processing on the colored seals with different colors, and further can improve the efficiency and the application universality of OCR character recognition on the target character images containing the colored seals.
Description
Technical Field
The application relates to the technical field of character recognition, in particular to a method and a device for filtering a colored seal in a character image.
Background
In recent years, the optical Character recognition (ocr) technology has been widely used in the financial fields such as banks, securities, and insurance. The OCR scene of the commercial bank is characterized in that printed certificates and bills to be recognized often carry colored seals. The colored seals often have certain influence on the accuracy of an OCR general deep learning (positioning and recognition) model, and considering that the mainstream OCR general positioning and recognition models in the industry and communities at present do not contain enough samples with the colored seals mostly during training, and the interference effect of the colored seals on the recognition result cannot be ignored.
For text images including colored seals, the current common practice in the OCR industry is to separate color channels of an initial color image by image preprocessing, strip out different primary color channels, and store the different primary color channels in different color channel matrixes respectively. And then, according to the actual seal color in the digital image in the specific scene, carrying out binarization processing on the corresponding color channel matrix, thereby achieving the effect of filtering the colored seal.
However, the limitation of the existing method is that the color information of the stamp in the image to be processed (i.e. what color the stamp to be filtered is) needs to be known in advance, so as to filter the colored stamp. However, various business scenes of commercial banks are very complicated, and red stamps and blue stamps can exist in various electronic bills or certificates of real banks. Among them, the red chapter is often found in the company and personal stamp related to domestic business, and the blue chapter is often found in the company and personal stamp related to overseas or hong kong and ao. Therefore, the colors of the seals in different business scenes of the bank are different, and the seals are difficult to exhaust and cannot be processed by a uniform and universal method. Particularly in the real business scene of banking, the color of the seal in the related bill or certificate may change. Once the color condition of the seal changes, the prior image preprocessing method needs to be correspondingly adjusted and modified. Therefore, the existing seal filtering method in the text and image cannot perform self-adaptive elimination processing on colored seals with different colors, and has defects in the aspects of universality, flexibility and the like.
Disclosure of Invention
Aiming at the problems in the prior art, the application provides a method and a device for filtering out colored seals in character images, which can perform adaptive elimination processing on colored seals with different colors, and further can improve the efficiency and the application universality of OCR character recognition on target character images containing the colored seals.
In order to solve the technical problem, the application provides the following technical scheme:
in a first aspect, the present application provides a method for filtering a colored stamp in a text image, including:
carrying out pixel superposition processing on binarization matrixes corresponding to three primary color channels of a target character image comprising a colored stamp to obtain a superposition fusion matrix of the target character image;
and acquiring a standard pixel value matrix corresponding to the superposition fusion matrix, and performing binarization processing on the standard pixel value matrix to obtain a gray level character image with the colored seal filtered out so as to acquire an OCR character recognition result of the gray level character image.
Further, before the pixel superposition processing is performed on the binarization matrixes corresponding to the three primary color channels of the target character image including the colored stamp, the method further includes:
acquiring a target character image comprising a colored seal;
judging whether the number of RGB channels in the target character image is 3 or not by applying a preset RGB primary color model, if so, performing color channel separation processing on the target character image to obtain channel matrixes corresponding to the three primary color channels of the target character image;
and respectively carrying out binarization processing on the channel matrixes respectively corresponding to the three primary color channels to obtain binarization matrixes respectively corresponding to the three primary color channels of the target character image.
Further, still include:
and if the number of the RGB channels in the target character image is judged to be not 3, outputting prompt information for indicating that the processing cannot be carried out according to the current format of the target image.
Further, the obtaining of the standard pixel value matrix corresponding to the superposition fusion matrix includes:
and resetting each pixel value with the numerical value larger than 255 in the superposition fusion matrix to be 255 respectively to obtain a standard pixel value matrix corresponding to the superposition fusion matrix.
Further, before the binarization processing is performed on the standard pixel value matrix to obtain the gray level character image with the colored seal filtered, the method further includes:
acquiring a shared threshold value for binarization processing;
correspondingly, the binarization processing is performed on the standard pixel value matrix to obtain the gray level character image with the colored seal filtered, and the method comprises the following steps:
and automatically carrying out binarization processing on the standard pixel value matrix based on the shared threshold value to obtain a gray level character image with the colored seal filtered.
In a second aspect, the present application provides a device for filtering a colored stamp in a text image, including:
the pixel superposition module is used for carrying out pixel superposition processing on binarization matrixes corresponding to three primary color channels of a target character image comprising a colored stamp to obtain a superposition fusion matrix of the target character image;
and the seal filtering module is used for acquiring a standard pixel value matrix corresponding to the superposition fusion matrix, and carrying out binarization processing on the standard pixel value matrix to obtain a gray level character image after the colored seal is filtered out so as to acquire an OCR character recognition result of the gray level character image.
Further, still include:
the image acquisition module is used for acquiring a target character image comprising the colored seal;
the color channel separation module is used for judging whether the number of RGB channels in the target character image is 3 by applying a preset RGB primary color model, and if so, performing color channel separation processing on the target character image to obtain channel matrixes corresponding to the three primary color channels of the target character image;
and the binarization matrix acquisition module is used for respectively carrying out binarization processing on the channel matrixes corresponding to the three-primary color channels to obtain the binarization matrixes corresponding to the three-primary color channels of the target character image.
Further, still include:
and the prompt information sending module is used for outputting prompt information used for indicating that the processing cannot be performed according to the current format of the target image if the judgment shows that the number of the RGB channels in the target character image is not 3.
Further, the seal filtering module includes:
and the pixel normalization unit is used for respectively resetting each pixel value of which the numerical value is greater than 255 in the superposition fusion matrix to be 255 so as to obtain a standard pixel value matrix corresponding to the superposition fusion matrix.
Further, still include:
the threshold setting module is used for acquiring a shared threshold for binarization processing;
correspondingly, the seal filtering module comprises:
and the binarization unit is used for automatically carrying out binarization processing on the standard pixel value matrix based on the shared threshold value to obtain the gray level character image with the colored seal filtered.
In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the step of the method for filtering out a colored stamp in a text image when executing the program.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the steps of the method for filtering out a colored stamp in a text image.
According to the technical scheme, the method and the device for filtering the colored seal in the text image provided by the application comprise the following steps: carrying out pixel superposition processing on binarization matrixes corresponding to three primary color channels of a target character image comprising a colored stamp to obtain a superposition fusion matrix of the target character image; the method comprises the steps of obtaining a standard pixel value matrix corresponding to the superposition fusion matrix, carrying out binarization processing on the standard pixel value matrix, obtaining a gray level character image after filtering the colored seal, obtaining an OCR character recognition result of the gray level character image, carrying out self-adaptive elimination processing on the colored seals with different colors, automatically filtering the seals with different colors in the character image, and not needing to carry out algorithm adjustment in advance according to the colors of the seals, so that the self-adaptability, flexibility and processing efficiency of seal filtering can be improved, and further the efficiency and the applicability of OCR character recognition on target character images containing the colored seals can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for filtering out a colored stamp in a text image in the embodiment of the present application.
Fig. 2 is a flowchart illustrating a method for filtering out a colored stamp in a text image including steps 010 to 040 in the embodiment of the present application.
Fig. 3 is a schematic flowchart of a method for filtering out a colored stamp in a text image including step 050 in this embodiment of the present application.
Fig. 4 is a schematic flowchart of a step 200 in a method for filtering out a colored stamp in a text image in the embodiment of the present application.
Fig. 5 is a flowchart illustrating a method for filtering out a colored stamp in a text image including step 060 and step 221 in this embodiment of the present application.
Fig. 6 is a schematic diagram of a specific implementation flow of filtering out a colored stamp in an electronic bank note or voucher in an application example of the present application.
Fig. 7 is a first structural schematic diagram of a device for filtering out a colored stamp in a text image in the embodiment of the present application.
Fig. 8 is a second structural schematic diagram of a device for filtering out a colored stamp in a text image in the embodiment of the present application.
Fig. 9 is a third structural schematic diagram of a device for filtering out a colored stamp in a text image in the embodiment of the present application.
Fig. 10 is a schematic structural diagram of a device for filtering out a colored stamp in a text image including a pixel normalization unit according to an embodiment of the present application.
Fig. 11 is a schematic structural diagram of a device for filtering out a colored stamp in a text image including a threshold setting module and a binarization unit in the embodiment of the application.
Fig. 12 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The embodiment of the application aims to provide a general image preprocessing algorithm for a text image comprising a colored stamp. The algorithm can be well attached to an OCR scene, not only is the seal color information of a character image not required to be clear in advance, but also the color change of a business seal in the character image can be adaptively responded to a certain degree, and common red seals, blue seals and the like in the character image are dynamically filtered.
In one or more embodiments of the present application, the text image refers to an image containing text information, and the colored stamp in the text image refers to a stamp with color. For example, the three primary color pixel values (R, G, B) of pure red are (255, 0, 0), the three primary color pixel values (R, G, B) of pure blue are (0, 0, 255), and the three primary color pixel values (R, G, B) of pure green are (0, 255, 0), which are all within the color range of the colored stamp of the present application, and of course, the colored stamp provided by the present application is also applicable to other colors, such as a color in which one primary color pixel value is greater than the preset pixel threshold value, or a color in which two primary color pixel values are greater than the preset pixel threshold value.
In daily application, a red stamp and a blue stamp are common colored stamps, especially in the financial field, so in a specific example of the present application, the method for filtering out colored stamps in text images provided by the present application can be a general image preprocessing algorithm specially used for filtering out colored stamps of bills and vouchers of bank electronics (note: here, the color stamps are generated by a scanner, a fax machine, and other special devices, and a photographed article is not in the scope of the present patent). The algorithm can better fit the related OCR scenes of commercial banks, not only does not need to define the seal color information in electronic bills and certificates in advance, but also can adaptively respond to the color change of business seals in the bank scenes to a certain extent, and dynamically filters the common red seals and blue seals of bank businesses. That is, a specific example of the target text image may be an image containing text, such as an electronic bank note or a certificate.
In order to automatically eliminate the influence of color in a colored stamp on stamp filtering, an embodiment of the present application provides a method for filtering a colored stamp in a text image, and referring to fig. 1, the method for filtering a colored stamp in a text image specifically includes the following contents:
step 100: and carrying out pixel superposition processing on binarization matrixes respectively corresponding to three primary color channels of the target character image comprising the colored stamp to obtain a superposition fusion matrix of the target character image.
In step 100, the three primary color channels refer to RGB three primary color channels, which are a Red channel, a Green channel, and a Blue channel, respectively.
It can be understood that the pixel superposition processing method in the present application may apply a preset pixel superposition mode for processing, for example, an "superposition" mode of Adobe photoshop, and in a preferred embodiment of the present application, OpenCV may be used to realize superposition of binarization matrices corresponding to respective channels of three primary colors of a target text image, where OpenCV is a cross-platform computer vision library issued based on BSD license (open source), and may run on Linux, Windows, Android, and Mac OS operating systems. Due to the characteristics of light weight and high efficiency of OpenCV, the superposition efficiency of the binarization matrixes corresponding to the three primary color channels of the target character image can be effectively improved, and the adaptivity, flexibility and processing efficiency of seal filtering can be further improved.
Step 200: and acquiring a standard pixel value matrix corresponding to the superposition fusion matrix, and performing binarization processing on the standard pixel value matrix to obtain a gray level character image with the colored seal filtered out so as to acquire an OCR character recognition result of the gray level character image.
In step 200, the standard pixel value matrix is a matrix obtained by applying a preset pixel value normalization processing manner to normalize the superposition fusion matrix, and the pixel value normalization processing manner may be preset according to actual needs, for example, each pixel value in the superposition fusion matrix whose value is greater than a preset value may be respectively reset to a fixed value, so that all pixel values in the superposition fusion matrix are less than or equal to the fixed value.
As can be seen from the above description, the method for filtering out colored stamps in text images provided in the embodiment of the present application can perform adaptive elimination processing on colored stamps with different colors by performing fusion, superposition and fusion processing on a binarization matrix, can automatically filter out the stamps with different colors in the text images, and does not need to perform algorithm adjustment in advance according to the colors of the stamps, and can improve the adaptivity, flexibility and processing efficiency of stamp filtering, thereby improving the efficiency and applicability of OCR character recognition on target text images including the colored stamps.
In order to effectively improve the reliability and efficiency of obtaining the binary matrix, in an embodiment of the method for filtering out a colored stamp in a text image provided by the present application, referring to fig. 2, before step 100, the method for filtering out a colored stamp in a text image further includes the following steps:
step 010: and acquiring a target character image comprising the colored seal.
In the step 010, the specific way of obtaining the target character image including the colored seal may be to receive a character recognition instruction sent by the user terminal device, and extract the target character image including the colored seal in the character recognition instruction, in this process, compared with the prior art that a processing way of distinguishing the colored seal is needed first, the method for filtering out the colored seal in the character image provided by the present application can completely omit this step, does not need to pre-judge the color of the colored seal, and directly executes the following step 020.
Step 020: and (3) judging whether the number of RGB channels in the target character image is 3 or not by using a preset RGB primary color model, and if so, executing a step 030.
Step 030: and carrying out color channel separation processing on the target character image to obtain channel matrixes corresponding to the three primary color channels of the target character image.
Step 040: and respectively carrying out binarization processing on the channel matrixes respectively corresponding to the three primary color channels to obtain binarization matrixes respectively corresponding to the three primary color channels of the target character image.
From the above description, the method for filtering out the colored seal in the character image provided by the embodiment of the application can effectively improve the reliability and efficiency of obtaining the binary matrix, provide a more accurate data base for the subsequent filtering out of the seal, and further improve the accuracy of OCR character recognition.
In order to timely and express that a user who initiates image filtering can be accurately notified when an image cannot be subjected to seal filtering processing, in an embodiment of the method for filtering a colored seal in a text image provided by the present application, referring to fig. 3, the method for filtering a colored seal in a text image after step 030 may further specifically include the following steps:
if the judgment of the step 020 shows that the number of the RGB channels in the target character image is not 3, executing a step 050: and if the number of the RGB channels in the target character image is judged to be not 3, outputting prompt information for indicating that the processing cannot be carried out according to the current format of the target image.
From the above description, it can be seen that the method for filtering out a colored seal in a text image provided in the embodiment of the present application can timely and accurately inform a user initiating image filtering when the image cannot be processed to filter out the seal, so that the user can check or replace a target image in time, and further user experience is effectively improved.
In order to effectively simplify the obtaining manner of the standard pixel value matrix on the basis of ensuring the accuracy of the obtaining result of the standard pixel value matrix, in an embodiment of the method for filtering out a colored stamp in a text image provided by the present application, referring to fig. 4, step 200 of the method for filtering out a colored stamp in a text image specifically includes the following contents:
step 210: and resetting each pixel value with the numerical value larger than 255 in the superposition fusion matrix to be 255 respectively to obtain a standard pixel value matrix corresponding to the superposition fusion matrix.
Step 220: and carrying out binarization processing on the standard pixel value matrix to obtain a gray level character image with the colored seal filtered.
As can be seen from the above description, the method for filtering out a colored stamp in a text image provided in the embodiment of the present application can effectively simplify the obtaining manner of the standard pixel value matrix on the basis of ensuring the accuracy of the obtaining result of the standard pixel value matrix, and further can effectively reduce the generation calculation amount of the standard pixel value matrix and improve the efficiency of obtaining the standard pixel value matrix.
In order to further improve the efficiency of binarization processing, in an embodiment of the method for filtering out a colored stamp in a text image provided by the present application, referring to fig. 5, before step 200 or step 100, the method for filtering out a colored stamp in a text image further includes the following steps:
step 060: a shared threshold value for binarization processing is acquired.
It is understood that the sharing threshold can be generally set between 130 and 160.
Correspondingly, the step 220 further includes the following steps:
step 221: and automatically carrying out binarization processing on the standard pixel value matrix based on the shared threshold value to obtain a gray level character image with the colored seal filtered.
As can be seen from the above description, the method for filtering out a colored stamp in a text image provided in the embodiment of the present application effectively improves the efficiency of binarization processing by receiving a shared threshold value sent by a user or set for storage in advance.
In order to further explain the scheme, the application also provides a specific application example of the method for filtering the colored seal in the character image by using the filtering device of the colored seal in the character image, and the application example relates to a general image preprocessing algorithm for filtering the colored seal of the electronic bank note or the voucher, in particular to the method for filtering the red or blue seal which is relatively common in banking business in a self-adaptive manner. The method specifically comprises the following steps:
the general idea of filtering colored seals in bank electronic bills or vouchers is as follows:
1) the method comprises the steps of eliminating the dependence of an algorithm on colors to be processed by performing pixel superposition fusion on a binarization processing result matrix of RGB three-primary color channels of a color picture;
2) the target matrix corresponds to the gray format picture. In the RGB primary color model, the red (or blue) pixel has a larger pixel value in the corresponding channel matrix, so that the corresponding position of the superposition fusion matrix also has a larger pixel value; for black (or dark) character parts, the pixel values of the black (or dark) character parts in the three-primary-color channel matrix are lower, so that the black (or dark) character parts have smaller pixel values at corresponding positions of the superposition fusion matrix;
and (4) carrying out normalization processing on each pixel in the matrix after superposition and fusion (ensuring the value to be within the range of 0-255), and carrying out binarization conversion on the matrix to obtain a target gray level picture. In the gray format picture, the color of the picture is lighter when the pixel value is larger (255 corresponds to white), and the color of the picture is darker when the pixel value is smaller (0 corresponds to black). Therefore, the pixel with a larger value (corresponding to the color seal) in the superimposed matrix is white in the target gray level picture after binarization, and the pixel with a smaller value (corresponding to the black or dark character) in the superimposed matrix is black in the target gray level picture after binarization.
Referring to fig. 6, the specific implementation process of filtering out the colored seal in the electronic bank bill or voucher:
1) inputting: original electronic bill, voucher color picture I _ img, with red or blue seal.
2) And (3) outputting: and filtering out the gray picture O _ img of the color seal.
3) The algorithm comprises the following steps:
(a) and loading the input picture I _ img in an RGB primary color model mode.
(b) It is determined whether the number of I _ img channels is equal to 3.
(c) If the judgment result is false, quitting and returning to the prompt message of 'picture format is not in compliance'; and if the judgment is true, continuing the subsequent processing.
(d) And performing color channel separation on the input picture I _ img to obtain corresponding three-primary-color channel matrixes C _ red, C _ green and C _ blue.
(e) And respectively carrying out binarization processing on the C _ red, the C _ green and the C _ blue to obtain corresponding binarization results thresh _ red, thresh _ green and thresh _ blue.
(f) And superposing the three-channel binary matrix thresh _ red, thresh _ green and thresh _ blue to obtain a superposed fusion matrix comb.
(g) And carrying out pixel value normalization processing on the comb matrix, and resetting the pixel value to be 255 when the pixel value is larger than 255 to obtain comb _ reg.
(h) And carrying out binarization processing on the comb _ reg matrix, and outputting a target picture O _ img according to a gray map format.
In a specific example of the method for filtering out the colored seal in the text image, the related algorithm is based on an opencv image library, and a calling mode with good encapsulation is provided. In the specific implementation and use process, the picture file storage path of the electronic bill and the certificate is transmitted, and the sharing threshold value of the binarization processing is set. Generally, the binary threshold value is set to be 130-160 for the electronic picture.
From the above description, it can be known that the method for filtering the colored seal in the text image provided by the application example of the present application can filter the seal without determining the seal color in the bank electronic bill or the certificate in advance, and can adaptively filter the red seal and the blue seal commonly found in the banking business to a certain extent. The algorithm design idea is simple and the use is convenient.
From the software aspect, in order to automatically eliminate the influence of the color in the colored stamp on stamp filtering, the present application further provides an embodiment of a device for filtering a colored stamp in a text image of all or partial contents in a method for filtering a colored stamp in a text image, see fig. 7, where the device for filtering a colored stamp in a text image specifically includes the following contents:
the pixel superposition module 10 is configured to perform pixel superposition processing on binarization matrices corresponding to respective three primary color channels of a target text image including a colored stamp to obtain a superposition fusion matrix of the target text image.
And a seal filtering module 20, configured to obtain a standard pixel value matrix corresponding to the superposition fusion matrix, and perform binarization processing on the standard pixel value matrix to obtain a grayscale character image from which the colored seal is filtered, so as to obtain an OCR character recognition result of the grayscale character image.
It can be known from the above description that the filtering device of colored seal in character image that this application embodiment provided, through fusing stack fusion processing to binary matrix, can carry out the self-adaptation elimination to the colored seal of different colours, can the seal of different colours in the automatic filtering character image, and need not to carry out algorithm adjustment according to the seal colour in advance, can improve the self-adaptation, the flexibility and the treatment effeciency of seal filtering, and then can improve the efficiency and the suitability extensive nature of carrying out OCR characters discernment to the target character image that contains colored seal.
In order to effectively improve the reliability and efficiency of obtaining the binary matrix, in an embodiment of the device for filtering a colored stamp in a text image provided by the present application, referring to fig. 8, the device for filtering a colored stamp in a text image further includes the following contents:
and the image acquisition module 01 is used for acquiring a target character image comprising the colored seal.
And the color channel separation module 02 is configured to apply a preset RGB primary color model to determine whether the number of RGB channels in the target text image is 3, and if so, perform color channel separation processing on the target text image to obtain channel matrices corresponding to the respective three primary color channels of the target text image.
A binarization matrix obtaining module 03, configured to perform binarization processing on the channel matrices corresponding to the three primary color channels, respectively, to obtain binarization matrices corresponding to the three primary color channels of the target text image, respectively.
From the above description, the filtering device for the colored seal in the character image provided by the embodiment of the application can effectively improve the reliability and efficiency of obtaining the binary matrix, provide a more accurate data base for the subsequent filtering seal, and further improve the accuracy of OCR character recognition.
In order to timely and express that a user who initiates image filtering can be accurately notified when an image cannot be processed by filtering a seal, in an embodiment of the device for filtering a colored seal in a text image provided by the present application, referring to fig. 9, the device for filtering a colored seal in a text image may further specifically include the following contents:
and the prompt information sending module 04 is configured to, if it is determined that the number of RGB channels in the target text image is not 3, output prompt information indicating that processing cannot be performed on the current format of the target text image.
It can be known from the above description that the filtering device for the colored seal in the text image provided by the embodiment of the application can timely and accurately inform the user who initiates the image filtering of the image in an expression manner when the image cannot be subjected to filtering seal processing, so that the user can check or replace the target image in time, and further the user experience is effectively improved.
In order to effectively simplify the obtaining manner of the standard pixel value matrix on the basis of ensuring the accuracy of the obtaining result of the standard pixel value matrix, in an embodiment of the device for filtering a colored stamp in a text image provided by the present application, referring to fig. 10, a stamp filtering module 20 of the device for filtering a colored stamp in a text image specifically includes the following contents:
the pixel normalization unit 21 is configured to reset each pixel value of the superimposed fusion matrix whose value is greater than 255 to 255, so as to obtain a standard pixel value matrix corresponding to the superimposed fusion matrix.
As can be seen from the above description, the device for filtering out a colored stamp in a text image provided in the embodiment of the present application can effectively simplify the obtaining manner of the standard pixel value matrix on the basis of ensuring the accuracy of the obtaining result of the standard pixel value matrix, and further can effectively reduce the generation calculation amount of the standard pixel value matrix and improve the efficiency of obtaining the standard pixel value matrix.
In order to further improve the efficiency of the binarization processing, in an embodiment of the device for filtering out a colored stamp in a text image provided by the present application, referring to fig. 11, the device for filtering out a colored stamp in a text image further includes the following contents:
and a threshold setting module 05, configured to acquire a shared threshold used for binarization processing.
Correspondingly, the seal filtering module 20 further includes the following contents:
and the binarization unit 22 is configured to automatically perform binarization processing on the standard pixel value matrix based on the shared threshold value to obtain a grayscale text image with the colored seal filtered.
As can be seen from the above description, the filtering device for a colored stamp in a text image provided in the embodiment of the present application effectively improves the efficiency of binarization processing by receiving a shared threshold value sent by a user or set for storage in advance.
In order to perform adaptive elimination processing on colored seals with different colors and further improve efficiency and applicability of OCR character recognition on a target character image including the colored seals, an embodiment of an electronic device for implementing all or part of contents in a method for filtering out colored seals in the character image is provided in the present application, where the electronic device specifically includes the following contents:
a processor (processor), a memory (memory), a communication Interface (Communications Interface), and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the communication interface is used for realizing information transmission between the electronic equipment and the user terminal and relevant equipment such as a relevant database and the like; the electronic device may be a desktop computer, a tablet computer, a mobile terminal, and the like, but the embodiment is not limited thereto. In this embodiment, the electronic device may be implemented with reference to the embodiment of the method for filtering out a colored stamp in a text image and the embodiment of the device for filtering out a colored stamp in a text image in the embodiment, and the contents thereof are incorporated herein, and repeated details are not repeated here.
Fig. 12 is a schematic block diagram of a system configuration of an electronic device 9600 according to an embodiment of the present application. As shown in fig. 12, the electronic device 9600 can include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. Notably, this fig. 12 is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.
In one embodiment, the function of filtering the colored stamp in the text image can be integrated into the central processing unit. Wherein the central processor may be configured to control:
step 100: and carrying out pixel superposition processing on binarization matrixes respectively corresponding to three primary color channels of the target character image comprising the colored stamp to obtain a superposition fusion matrix of the target character image.
In step 100, the three primary color channels refer to RGB three primary color channels, which are a Red channel, a Green channel, and a Blue channel, respectively.
It can be understood that the pixel superposition processing method in the present application may apply a preset pixel superposition mode for processing, for example, an "superposition" mode of Adobe photoshop, and in a preferred embodiment of the present application, OpenCV may be used to realize superposition of binarization matrices corresponding to respective channels of three primary colors of a target text image, where OpenCV is a cross-platform computer vision library issued based on BSD license (open source), and may run on Linux, Windows, Android, and Mac OS operating systems. Due to the characteristics of light weight and high efficiency of OpenCV, the superposition efficiency of the binarization matrixes corresponding to the three primary color channels of the target character image can be effectively improved, and the adaptivity, flexibility and processing efficiency of seal filtering can be further improved.
Step 200: and acquiring a standard pixel value matrix corresponding to the superposition fusion matrix, and performing binarization processing on the standard pixel value matrix to obtain a gray level character image with the colored seal filtered out so as to acquire an OCR character recognition result of the gray level character image.
In step 200, the standard pixel value matrix is a matrix obtained by applying a preset pixel value normalization processing manner to normalize the superposition fusion matrix, and the pixel value normalization processing manner may be preset according to actual needs, for example, each pixel value in the superposition fusion matrix whose value is greater than a preset value may be respectively reset to a fixed value, so that all pixel values in the superposition fusion matrix are less than or equal to the fixed value.
From the above description, the electronic device provided in the embodiment of the present application can perform adaptive elimination processing on colored seals with different colors by fusing, superimposing, and fusing the binary matrix, can automatically filter the seals with different colors in the text image, and does not need to perform algorithm adjustment in advance according to the colors of the seals, and can improve the adaptivity, flexibility, and processing efficiency of the seal filtering, and further can improve the efficiency and the applicability of OCR character recognition on the target text image including the colored seals.
In another embodiment, the filtering device for the colored stamp in the text image may be configured separately from the central processing unit 9100, for example, the filtering device for the colored stamp in the text image may be configured as a chip connected to the central processing unit 9100, and the filtering function for the colored stamp in the text image is realized by the control of the central processing unit.
As shown in fig. 12, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that the electronic device 9600 also does not necessarily include all of the components shown in fig. 12; further, the electronic device 9600 may further include components not shown in fig. 12, which can be referred to in the related art.
As shown in fig. 12, a central processor 9100, sometimes referred to as a controller or operational control, can include a microprocessor or other processor device and/or logic device, which central processor 9100 receives input and controls the operation of the various components of the electronic device 9600.
The memory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 9100 can execute the program stored in the memory 9140 to realize information storage or processing, or the like.
The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. Power supply 9170 is used to provide power to electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, an LCD display, but is not limited thereto.
The memory 9140 can be a solid state memory, e.g., Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 9140 could also be some other type of device. Memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 being used for storing application programs and function programs or for executing a flow of operations of the electronic device 9600 by the central processor 9100.
The memory 9140 can also include a data store 9143, the data store 9143 being used to store data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers for the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, contact book applications, etc.).
The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing ordinary telecommunications functions. The audio processor 9130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100, thereby enabling recording locally through the microphone 9132 and enabling locally stored sounds to be played through the speaker 9131.
An embodiment of the present application further provides a computer-readable storage medium capable of implementing all steps in the method for filtering out a colored stamp in a text image in the foregoing embodiment, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all steps of the method for filtering out a colored stamp in a text image where an execution subject is a server or a client in the foregoing embodiment are implemented, for example, when the processor executes the computer program, the following steps are implemented:
step 100: and carrying out pixel superposition processing on binarization matrixes respectively corresponding to three primary color channels of the target character image comprising the colored stamp to obtain a superposition fusion matrix of the target character image.
In step 100, the three primary color channels refer to RGB three primary color channels, which are a Red channel, a Green channel, and a Blue channel, respectively.
It can be understood that the pixel superposition processing method in the present application may apply a preset pixel superposition mode for processing, for example, an "superposition" mode of Adobe photoshop, and in a preferred embodiment of the present application, OpenCV may be used to realize superposition of binarization matrices corresponding to respective channels of three primary colors of a target text image, where OpenCV is a cross-platform computer vision library issued based on BSD license (open source), and may run on Linux, Windows, Android, and Mac OS operating systems. Due to the characteristics of light weight and high efficiency of OpenCV, the superposition efficiency of the binarization matrixes corresponding to the three primary color channels of the target character image can be effectively improved, and the adaptivity, flexibility and processing efficiency of seal filtering can be further improved.
Step 200: and acquiring a standard pixel value matrix corresponding to the superposition fusion matrix, and performing binarization processing on the standard pixel value matrix to obtain a gray level character image with the colored seal filtered out so as to acquire an OCR character recognition result of the gray level character image.
In step 200, the standard pixel value matrix is a matrix obtained by applying a preset pixel value normalization processing manner to normalize the superposition fusion matrix, and the pixel value normalization processing manner may be preset according to actual needs, for example, each pixel value in the superposition fusion matrix whose value is greater than a preset value may be respectively reset to a fixed value, so that all pixel values in the superposition fusion matrix are less than or equal to the fixed value.
As can be seen from the above description, the computer-readable storage medium provided in the embodiment of the present application, through fusing, superimposing, and fusing the binarization matrix, can perform adaptive elimination processing on colored stamps with different colors, can automatically filter the stamps with different colors in the text image, and does not need to perform algorithm adjustment in advance according to the color of the stamp, and can improve the adaptivity, flexibility, and processing efficiency of the stamp filtering, and further can improve the efficiency and the applicability of performing OCR character recognition on a target text image including the colored stamp.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. 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 principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (12)
1. A method for filtering out colored seals in character images is characterized by comprising the following steps:
carrying out pixel superposition processing on binarization matrixes corresponding to three primary color channels of a target character image comprising a colored stamp to obtain a superposition fusion matrix of the target character image;
and acquiring a standard pixel value matrix corresponding to the superposition fusion matrix, and performing binarization processing on the standard pixel value matrix to obtain a gray level character image with the colored seal filtered out so as to acquire an OCR character recognition result of the gray level character image.
2. The method for filtering out colored stamps in a text image according to claim 1, wherein before the pixel superposition processing is performed on the binarized matrices corresponding to the respective channels of the three primary colors of the target text image including the colored stamps, the method further comprises:
acquiring a target character image comprising a colored seal;
judging whether the number of RGB channels in the target character image is 3 or not by applying a preset RGB primary color model, if so, performing color channel separation processing on the target character image to obtain channel matrixes corresponding to the three primary color channels of the target character image;
and respectively carrying out binarization processing on the channel matrixes respectively corresponding to the three primary color channels to obtain binarization matrixes respectively corresponding to the three primary color channels of the target character image.
3. The method for filtering out colored stamps in text images according to claim 2, further comprising:
and if the number of the RGB channels in the target character image is judged to be not 3, outputting prompt information for indicating that the processing cannot be carried out according to the current format of the target image.
4. The method for filtering out colored stamps in text images according to claim 1, wherein the obtaining of the standard pixel value matrix corresponding to the superposition fusion matrix comprises:
and resetting each pixel value with the numerical value larger than 255 in the superposition fusion matrix to be 255 respectively to obtain a standard pixel value matrix corresponding to the superposition fusion matrix.
5. The method according to claim 1, wherein before the binarizing processing is performed on the standard pixel value matrix to obtain the gray level text image with the colored stamp filtered, the method further comprises:
acquiring a shared threshold value for binarization processing;
correspondingly, the binarization processing is performed on the standard pixel value matrix to obtain the gray level character image with the colored seal filtered, and the method comprises the following steps:
and automatically carrying out binarization processing on the standard pixel value matrix based on the shared threshold value to obtain a gray level character image with the colored seal filtered.
6. A filtering device for colored seals in character images is characterized by comprising:
the pixel superposition module is used for carrying out pixel superposition processing on binarization matrixes corresponding to three primary color channels of a target character image comprising a colored stamp to obtain a superposition fusion matrix of the target character image;
and the seal filtering module is used for acquiring a standard pixel value matrix corresponding to the superposition fusion matrix, and carrying out binarization processing on the standard pixel value matrix to obtain a gray level character image after the colored seal is filtered out so as to acquire an OCR character recognition result of the gray level character image.
7. The apparatus for filtering out colored stamps in text images according to claim 6, further comprising:
the image acquisition module is used for acquiring a target character image comprising the colored seal;
the color channel separation module is used for judging whether the number of RGB channels in the target character image is 3 by applying a preset RGB primary color model, and if so, performing color channel separation processing on the target character image to obtain channel matrixes corresponding to the three primary color channels of the target character image;
and the binarization matrix acquisition module is used for respectively carrying out binarization processing on the channel matrixes corresponding to the three-primary color channels to obtain the binarization matrixes corresponding to the three-primary color channels of the target character image.
8. The apparatus for filtering out colored stamps in text images according to claim 7, further comprising:
and the prompt information sending module is used for outputting prompt information used for indicating that the processing cannot be performed according to the current format of the target image if the judgment shows that the number of the RGB channels in the target character image is not 3.
9. The device for filtering out colored stamps in textual images according to claim 6, wherein said stamp filtering module comprises:
and the pixel normalization unit is used for respectively resetting each pixel value of which the numerical value is greater than 255 in the superposition fusion matrix to be 255 so as to obtain a standard pixel value matrix corresponding to the superposition fusion matrix.
10. The apparatus for filtering out colored stamps in text images according to claim 6, further comprising:
the threshold setting module is used for acquiring a shared threshold for binarization processing;
correspondingly, the seal filtering module comprises:
and the binarization unit is used for automatically carrying out binarization processing on the standard pixel value matrix based on the shared threshold value to obtain the gray level character image with the colored seal filtered.
11. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for filtering out the colored stamp in the text image according to any one of claims 1 to 5 when executing the program.
12. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the method for filtering out a colored stamp in a text image according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010470474.8A CN111680694A (en) | 2020-05-28 | 2020-05-28 | Method and device for filtering colored seal in character image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010470474.8A CN111680694A (en) | 2020-05-28 | 2020-05-28 | Method and device for filtering colored seal in character image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111680694A true CN111680694A (en) | 2020-09-18 |
Family
ID=72453508
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010470474.8A Pending CN111680694A (en) | 2020-05-28 | 2020-05-28 | Method and device for filtering colored seal in character image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111680694A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112419471A (en) * | 2020-11-19 | 2021-02-26 | 腾讯科技（深圳）有限公司 | Data processing method and device, intelligent equipment and storage medium |
| CN113066223A (en) * | 2021-04-22 | 2021-07-02 | 中国工商银行股份有限公司 | Automatic invoice verification method and device |
| CN113128512A (en) * | 2021-04-14 | 2021-07-16 | 浪潮天元通信信息系统有限公司 | Method and tool for removing red seal based on color channel |
| CN113222843A (en) * | 2021-05-10 | 2021-08-06 | 北京有竹居网络技术有限公司 | Image restoration method and related equipment thereof |
| CN113312982A (en) * | 2021-05-07 | 2021-08-27 | 珠海金山办公软件有限公司 | Document restoration processing method and device, computer storage medium and terminal |
| CN114677337A (en) * | 2022-03-11 | 2022-06-28 | 常州市新创智能科技有限公司 | Method and device for detecting oil stains on carbon fiber cloth surface |
| CN114936965A (en) * | 2022-06-07 | 2022-08-23 | 上海弘玑信息技术有限公司 | Seal removing method, device, equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002142101A (en) * | 2000-11-06 | 2002-05-17 | Sharp Corp | Image processing device |
| CN109886974A (en) * | 2019-01-28 | 2019-06-14 | 北京易道博识科技有限公司 | A kind of seal minimizing technology |
-
2020
- 2020-05-28 CN CN202010470474.8A patent/CN111680694A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002142101A (en) * | 2000-11-06 | 2002-05-17 | Sharp Corp | Image processing device |
| CN109886974A (en) * | 2019-01-28 | 2019-06-14 | 北京易道博识科技有限公司 | A kind of seal minimizing technology |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112419471A (en) * | 2020-11-19 | 2021-02-26 | 腾讯科技（深圳）有限公司 | Data processing method and device, intelligent equipment and storage medium |
| CN112419471B (en) * | 2020-11-19 | 2024-04-26 | 腾讯科技（深圳）有限公司 | Data processing method and device, intelligent equipment and storage medium |
| CN113128512A (en) * | 2021-04-14 | 2021-07-16 | 浪潮天元通信信息系统有限公司 | Method and tool for removing red seal based on color channel |
| CN113066223A (en) * | 2021-04-22 | 2021-07-02 | 中国工商银行股份有限公司 | Automatic invoice verification method and device |
| CN113312982A (en) * | 2021-05-07 | 2021-08-27 | 珠海金山办公软件有限公司 | Document restoration processing method and device, computer storage medium and terminal |
| CN113222843A (en) * | 2021-05-10 | 2021-08-06 | 北京有竹居网络技术有限公司 | Image restoration method and related equipment thereof |
| CN113222843B (en) * | 2021-05-10 | 2023-11-10 | 北京有竹居网络技术有限公司 | Image restoration method and related equipment thereof |
| CN114677337A (en) * | 2022-03-11 | 2022-06-28 | 常州市新创智能科技有限公司 | Method and device for detecting oil stains on carbon fiber cloth surface |
| CN114677337B (en) * | 2022-03-11 | 2022-10-04 | 常州市新创智能科技有限公司 | Method and device for detecting oil stains on carbon fiber cloth surface |
| CN114936965A (en) * | 2022-06-07 | 2022-08-23 | 上海弘玑信息技术有限公司 | Seal removing method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111680694A (en) | Method and device for filtering colored seal in character image | |
| CN113168684B (en) | Method, system and computer readable medium for improving quality of low brightness images | |
| CN111652093B (en) | Text image processing method and device | |
| CN110766033B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN109741281B (en) | Image processing method, image processing device, storage medium and terminal | |
| CN111582273A (en) | Image text recognition method and device | |
| US11398016B2 (en) | Method, system, and computer-readable medium for improving quality of low-light images | |
| JP2021531571A (en) | Certificate image extraction method and terminal equipment | |
| CN113537819A (en) | Automatic service message checking method and device | |
| CN110599190A (en) | Identity authentication method and device based on block chain | |
| CN112861906A (en) | Method and device for detecting picture abnormity | |
| CN110880164B (en) | Image processing method, device, equipment and computer storage medium | |
| CN110020645B (en) | Image processing method and device, computing equipment and storage medium | |
| CN111428570A (en) | Detection method and device for non-living human face, computer equipment and storage medium | |
| CN114049264A (en) | Dim light image enhancement method and device, electronic equipment and storage medium | |
| CN110310341A (en) | The generation method of default parameters, device, equipment and storage medium in color algorithm | |
| CN115760879A (en) | Image processing method, image processing system, image processing apparatus, device, and medium | |
| US20220327849A1 (en) | Computer-Implemented Method For Optical Character Recognition | |
| US9349085B1 (en) | Methods and system to decode hidden images | |
| CN111798389A (en) | Self-adaptive image enhancement method and device | |
| CN110751053B (en) | Vehicle color identification method, device, equipment and storage medium | |
| CN108647747A (en) | OCR identifies and blocks close introduction method | |
| CN115174275B (en) | Remote control method and device based on cloud | |
| CN117094986B (en) | Self-adaptive defect detection method based on small sample and terminal equipment | |
| CN109284732B (en) | Picture reporting method and related device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200918 |