CN115063824A

CN115063824A - Bank card number identification method and device based on residual error network, and electronic equipment

Info

Publication number: CN115063824A
Application number: CN202210737703.7A
Authority: CN
Inventors: 王易檀; 辛丽娟; 张芬; 艾猛
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2022-06-27
Filing date: 2022-06-27
Publication date: 2022-09-16

Abstract

The disclosure provides a bank card number identification method, a bank card number identification device, electronic equipment and a storage medium based on a residual error network, which can be applied to the technical field of information processing, the financial field or other fields. The method comprises the following steps: preprocessing the acquired bank card image to be identified to generate a preprocessed image; determining a target area from the preprocessed image based on a preset rule, wherein the target area is associated with the type of the bank card, and the bank card number of the bank card to be identified is located in the target area; determining an edge area containing the card number characters from the target area through an edge detection algorithm, processing the edge area to generate a plurality of character images containing single card number characters; and inputting the plurality of character images into the trained residual error network for identification to generate an identification result of the bank card number.

Description

Bank card number identification method and device based on residual error network, and electronic equipment

Technical Field

The present disclosure relates to the field of information processing technologies, and in particular, to a method and an apparatus for identifying a bank card number based on a residual error network, an electronic device, and a readable storage medium.

Background

With the use of the bank card becoming more and more extensive, the cost of manually inputting a large number of bank card number pictures of the user by service providers such as banks is higher. Most of the bank card character recognition in the prior art adopts a template matching algorithm, namely, an image area matched with a template picture is searched for recognition, the searching time is long, the efficiency is low, and when the picture background changes, the effective recognition cannot be realized.

Disclosure of Invention

In view of the above problems, the present disclosure provides a method and an apparatus for identifying a bank card number based on a residual error network, an electronic device, and a storage medium. The recognition speed and the recognition precision can be effectively improved. The method includes but is not limited to: preprocessing the acquired bank card image to be identified to generate a preprocessed image; determining a target area from the preprocessed image based on a preset rule, wherein the target area is associated with the type of the bank card, and the bank card number of the bank card to be identified is located in the target area; determining an edge area containing the card number characters from the target area through an edge detection algorithm, processing the edge area, and generating a plurality of character images containing single card number characters; and inputting the character images into the trained residual error network for identification to generate an identification result of the bank card number.

In some embodiments of the present disclosure, the preprocessing the acquired bank card image to be recognized, and generating the preprocessed image includes: carrying out correction processing on the acquired bank card image to be identified; carrying out gray level processing on the image subjected to the correction processing to obtain a gray level image; and denoising the gray level image to generate a preprocessed image.

In some embodiments of the present disclosure, the determining a target region from the preprocessed image based on a preset rule includes: acquiring at least one set area of a preprocessed image according to the preset rule, wherein the set area is associated with the type of the bank card; detecting whether characters exist in the at least one set area; and determining the set area with the characters as a target area, wherein the bank card number of the bank card type associated with the target area is positioned in the target area.

In some embodiments of the disclosure, the determining, by an edge detection algorithm, an edge region containing a card number character from the target region comprises: traversing the pixels of the target area through an edge detection algorithm, and determining the gradient intensity and the gradient direction of the pixels; and determining the edge area of the card number characters from the target area according to the gradient strength, the gradient direction and the set threshold value.

In some embodiments of the disclosure, the determining, according to the gradient strength, the gradient direction and the set threshold, an edge region of a card number character from the target region includes: determining an edge point from the target area according to the gradient strength and the gradient direction, wherein the edge point has the maximum gradient strength in the same gradient direction; deleting the pixel points with the gradient intensity smaller than the set threshold; and filling the pixel points with the gradient strength within the set threshold value to determine the edge area of the card number character, wherein the edge points are located in the edge area.

In some embodiments of the disclosure, said processing for said edge region, generating a plurality of character images containing a single card number character, comprises: carrying out contour detection on the edge area; traversing the outlines of all the edge areas, and determining rectangular outlines containing all the card number characters of the bank card number; and dividing the rectangular outline according to the size of each edge area to generate a plurality of character images containing single card number characters.

In some embodiments of the present disclosure, the residual network comprises a ResNet56 residual network.

A second aspect of the present disclosure provides a bank card number identification device based on a residual error network, including but not limited to: the first generation module is configured to preprocess the acquired bank card image to be identified and generate a preprocessed image; the determining module is configured to determine a target area from the preprocessed image based on a preset rule, wherein the target area is associated with the type of the bank card, and the bank card number of the bank card to be identified is located in the target area; the second generation module is configured to determine an edge area containing the card number characters from the target area through an edge detection algorithm, process the edge area and generate a plurality of character images containing a single card number character; and the third generation module is configured to input the character images to the trained residual error network for recognition, and generate a recognition result of the bank card number.

In some exemplary embodiments of the present disclosure, the first generation module includes a first generation submodule configured to: carrying out correction processing on the acquired bank card image to be identified; carrying out gray level processing on the image subjected to the positive conversion processing to obtain a gray level image; and denoising the gray level image to generate a preprocessed image.

In some exemplary embodiments of the present disclosure, the determining module includes a determining submodule configured to: acquiring at least one set area of a preprocessed image according to the preset rule, wherein the set area is associated with the type of the bank card; detecting whether characters exist in the at least one set area; and determining the set area with the characters as a target area, wherein the bank card number of the bank card type associated with the target area is positioned in the target area.

In some exemplary embodiments of the present disclosure, the second generating module includes a first generating unit and a second generating unit, the first generating unit is configured to: traversing the pixels of the target area through an edge detection algorithm, and determining the gradient intensity and the gradient direction of the pixels; and determining the edge area of the card number characters from the target area according to the gradient strength, the gradient direction and the set threshold value.

In some exemplary embodiments of the present disclosure, the first generating unit includes a first generating subunit configured to: determining an edge point from the target area according to the gradient strength and the gradient direction, wherein the edge point has the maximum gradient strength in the same gradient direction; deleting the pixel points with the gradient intensity smaller than the set threshold; and filling the pixel points with the gradient intensity within the set threshold value to determine the edge area of the card number character, wherein the edge points are located in the edge area.

In some exemplary embodiments of the present disclosure, the second generating unit is configured to: carrying out contour detection on the edge area; traversing the outlines of all the edge areas, and determining rectangular outlines containing all the card number characters of the bank card number; and dividing the rectangular outline according to the size of each edge area to generate a plurality of character images containing single card number characters.

A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; a storage device for storing executable instructions that, when executed by the processor, implement the method according to the above.

A fourth aspect of the disclosure provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, implement a method according to the above.

A fifth aspect of the disclosure provides a computer program product comprising a computer program which, when executed by a processor, implements a method according to the above.

According to the embodiment of the disclosure, the target area is determined from the preprocessed image of the bank card to be recognized, the image area required to be processed in the subsequent recognition process can be reduced, the recognition speed is effectively improved, meanwhile, the target area is processed, the character image containing the single card number character is generated, the character image is recognized by adopting a residual error network, and the recognition precision can be effectively improved.

Drawings

The foregoing and other objects, features and advantages of the disclosure will be apparent from the following description of embodiments of the disclosure, which proceeds with reference to the accompanying drawings, in which:

fig. 1 is a schematic diagram schematically illustrating a system architecture to which a bank card number identification method based on a residual error network according to an embodiment of the present disclosure may be applied;

fig. 2 schematically shows a flow chart of a bank card number identification method based on a residual error network according to an embodiment of the disclosure;

fig. 3 schematically shows a flowchart of the residual error network-based bank card number identification method in operation S210 according to an embodiment of the present disclosure;

fig. 4 schematically shows a flowchart of the residual error network-based bank card number identification method in operation S220 according to an embodiment of the present disclosure;

fig. 5 schematically shows a flowchart of a residual error network-based bank card number identification method at operation S230 according to one embodiment of the present disclosure;

fig. 6 schematically shows a flowchart of the residual error network-based bank card number identification method at operation S232 according to an embodiment of the present disclosure;

fig. 7 schematically shows a flowchart of a residual error network-based bank card number identification method at operation S230 according to another embodiment of the present disclosure;

fig. 8 is a block diagram schematically illustrating the structure of a bank card number identification device based on a residual error network according to an embodiment of the disclosure; and

fig. 9 schematically shows a block diagram of an electronic device adapted to implement a residual error network-based bank card number identification method according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.

Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, necessary confidentiality measures are taken, and the customs of the public order is not violated.

In the technical scheme of the disclosure, the operations of obtaining, storing, applying and the like of the related user personal information all obtain the authorization of the user.

In an embodiment of the present disclosure, the term "edge region" refers to a region including an edge line determined by an edge detection algorithm. The edge line indicates the position in an image where the intensity of the gray scale is most strongly varied.

In order to solve the problems of long identification time and low identification precision in the related art, embodiments of the present disclosure provide a bank card number identification method and apparatus based on a residual error network, an electronic device, and a storage medium. The bank card number identification method based on the residual error network comprises the following steps: preprocessing the acquired bank card image to be identified to generate a preprocessed image; determining a target area from the preprocessed image based on a preset rule, wherein the target area is associated with the type of the bank card, and the bank card number of the bank card to be identified is located in the target area; determining an edge area containing the card number characters from the target area through an edge detection algorithm, processing the edge area to generate a plurality of character images containing single card number characters; and inputting the plurality of character images into the trained residual error network for identification to generate an identification result of the bank card number.

Fig. 1 is a schematic diagram schematically illustrating a system architecture to which the bank card number identification method based on the residual error network of the embodiment of the disclosure can be applied. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios. It should be noted that the method, the apparatus, the electronic device and the readable storage medium for identifying a bank card number based on a residual error network provided in the embodiments of the present disclosure may be used in related aspects in the information processing technology field and the financial field, and may also be used in various fields other than the information processing technology field or the financial field.

As shown in fig. 1, a system architecture 100 according to this embodiment may include a terminal device 101, an image capture device 102, a network 103, and a server 104.

The network 103 is used to provide a medium of communication links between the terminal apparatus 101, the image pickup apparatus 102, and the server 104. Network 103 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the terminal device 101, the image capturing device interacting with the server 104 via the network 103 to receive or send messages or the like. Various messaging client applications, such as data processing applications, web browser applications, search-type applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only) may be installed on terminal device 101.

The terminal device 101 may be various electronic devices having a display screen and supporting data processing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The image capturing apparatus 102 may be an electronic apparatus having an image data capturing function, such as an electronic camera, a scanning apparatus, an electronic copying apparatus, or the like.

The server 104 may be a server providing various services, such as a background management server (for example only) storing or processing data sent or written by the user using the terminal device 101 or the image capturing device 102. The background management server may analyze and/or otherwise process data such as the received user request, or may feed back a received user instruction, and feed back a processing result (e.g., information or data obtained according to the user request) to the terminal device.

It should be noted that the bank card number identification method based on the residual error network provided by the embodiment of the present disclosure may be generally executed by the server 104. Accordingly, the bank card number identification device based on the residual error network provided by the embodiment of the present disclosure may be generally disposed in the server 104. The bank card number identification method based on the residual error network provided by the embodiment of the disclosure can also be executed by a server or a server cluster which is different from the server 104 and can communicate with the terminal device 101, the image acquisition device 102 and/or the server 104. Correspondingly, the bank card number identification device based on the residual error network provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster that is different from the server 104 and can communicate with the terminal device 101, the image capture device 102 and/or the server 104.

It should be understood that the number of terminal devices, image capturing devices, networks, and servers in fig. 1 are merely illustrative. Any number of terminal devices, image capture devices, networks, and servers may be present, as desired for implementation.

The bank card number identification method based on the residual error network of the disclosed embodiment will be described in detail below with reference to fig. 2 to 7.

Fig. 2 schematically shows a flowchart of a bank card number identification method based on a residual error network according to an embodiment of the disclosure.

As shown in fig. 2, the flow 200 of the method for identifying a bank card number based on a residual error network of the present disclosure includes operations S210 to S240.

In operation S210, the acquired bank card image to be recognized is preprocessed, so as to generate a preprocessed image.

In the embodiment of the present disclosure, the bank card to be recognized may be obtained by the image acquisition device 102, for example, because the photos of the bank card to be recognized obtained by different devices are different, in the recognition process, the bank card image to be recognized needs to be preprocessed, so as to remove noise or interference information in the image, and the accuracy of the recognition of the bank card number can be effectively improved.

Fig. 3 schematically shows a flowchart of the residual error network-based bank card number identification method in operation S210 according to an embodiment of the present disclosure.

As shown in fig. 3, the flow of operation S210 may include operations S211 through S213.

In operation S211, the acquired bank card image to be recognized is subjected to a correction process.

In the embodiment of the disclosure, the positions of the bank card number and the corresponding bank card mark (for example, the unionpay mark) are different due to different acquisition modes or acquisition angles of the bank card in the acquired bank card image to be identified, and in the process of identifying the bank card number, the bank card image is corrected first, so that the bank card number at the position of the bank card number in the image can be identified more accurately.

In operation S212, the image after the alignment process is subjected to a gradation process to obtain a gradation image.

After performing gray scale processing on the image after the alignment processing, for example, converting the color image into a gray scale image by using a mean value weighting method, the gray scale value of the gray scale image can be determined according to formula 1:

gr is a × R + B × G + c × B formula 1

Gr represents the gray value of the obtained gray image, R represents the brightness value of a red pixel point, G represents the brightness value of a green pixel point, and B represents the brightness value of a blue pixel point. a. b and c represent weight values. Exemplarily, in the present embodiment, a is 0.3, b is 0.59, and c is 0.11, and by this weight, floating point operation can be effectively avoided, and the efficiency of the code is improved.

In operation S213, the grayscale image is denoised to generate a preprocessed image.

Illustratively, the input gray image is processed with a gaussian filter, for example, the image is subjected to smoothing filtering, so as to remove noise information in the image. Interference factors in the subsequent processing process can be reduced, and the identification accuracy is improved.

Fig. 4 schematically shows a flowchart of the bank card number identification method based on the residual error network in operation S220 according to an embodiment of the disclosure.

In operation S220, a target area is determined from the preprocessed image based on a preset rule, the target area is associated with the type of the bank card, and the bank card number of the bank card to be recognized is located in the target area.

As shown in fig. 4, operation S220 may include operations S221 through S223.

In operation S221, at least one set region of the preprocessed image is obtained according to a preset rule, and the set region is associated with a type of the bank card.

In the embodiment of the present disclosure, the preset rule is, for example, to determine the setting area of each type of bank card according to the type of the bank card, that is, each type of bank card has a corresponding setting area, where the setting area is an area including the card number of the type of bank card, and after the preprocessed image is obtained, the setting area of the preprocessed image is obtained according to the type of the bank card in the preset rule. When a plurality of bank card types exist in the preset rule, a plurality of setting areas can be obtained. In an alternative embodiment, when the setting areas in a plurality of bank card types are the same, only one setting area is obtained.

In operation S222, it is detected whether a character exists in at least one set region.

After the setting area is acquired, whether the setting area contains characters is further detected and judged. For example, the types of the bank cards are different, but the positions of the numbers of the bank cards may be the same, or the types of the bank cards and the set positions may have certain errors. Whether character information exists in the set area or not is further detected and judged, the non-bank card image can be quickly and accurately eliminated, and the processing speed is effectively improved.

In this embodiment, the character information may be, for example, a character image in a set area, and the character may be a numeric character, an english character, a kanji character, or another type of character.

In operation S223, the set region where the character exists is determined as a target region in which the bank card number of the bank card type associated with the target region is located.

When the character information exists in the set area, the set area with the character is determined as the target area. As described above, according to the preset rule, each kind of bank card has a bank card number at a position corresponding to the bank card, and after the preprocessed image is obtained by presetting an area where each kind of bank card number is located, the corresponding set area of the preprocessed image is detected whether characters exist or not according to the set area corresponding to each kind, and when the characters exist, the area is determined as a target area, that is, the bank card number in the target area is preliminarily determined, that is, the bank card number in the kind is located in the target area.

According to the embodiment of the disclosure, the target area with the bank card number can be quickly positioned, and the area of the target area is smaller than that of the pre-processed image, so that the data processing amount can be reduced, the image processing speed is improved, and the efficiency of identifying the bank card number is effectively improved in the process of carrying out subsequent image processing.

In operation S230, an edge region containing the card number characters is determined from the target region by an edge detection algorithm, and the edge region is processed to generate a plurality of character images containing a single card number character.

In the embodiment of the disclosure, after the target area is determined, the target area is processed through an edge detection algorithm to determine an edge area containing the card number characters. That is, only the edge detection processing is performed on the target area, so that the data processing amount can be effectively reduced, and the processing efficiency can be improved. The target area contains the bank card number, so that after the target area is processed, the edge area containing the card number character can be effectively determined.

In the embodiment of the disclosure, after the edge area is determined, the edge area is further processed, for example, a rectangular outline of the edge area is determined, and the rectangular outline is divided, so as to generate a plurality of character images, where each character image includes a card number character, such as a numeric character or an english character, or other characters.

Operation S230 is described in detail below with reference to fig. 5 to 7.

Fig. 5 schematically shows a flowchart of the residual error network-based bank card number identification method at operation S230 according to one embodiment of the present disclosure. Fig. 6 schematically shows a flowchart of the bank card number identification method based on the residual error network in operation S232 according to the embodiment of the disclosure. Fig. 7 schematically shows a flowchart of a residual error network-based bank card number identification method in operation S230 according to another embodiment of the present disclosure.

As shown in fig. 5, determining an edge region containing the card number characters from the target region through the edge detection algorithm in operation S230 may include operations S231 through S232.

In operation S231, pixels of the target region are traversed by the edge detection algorithm, and gradient strength and gradient direction of the pixels are determined.

In the embodiment of the disclosure, the edge detection algorithm may be, for example, edge detection by using a sobel operator, the algorithm is relatively simple, the texture is not concerned much in the process of identifying the bank card number, and by adopting the sobel edge detection algorithm, efficient calculation can be realized, and the identification speed is increased.

Illustratively, in the edge detection, for each pixel point of the target area, a sobel horizontal operator sobel is used _x And vertical operator sobel _y Convolution of input image to calculate transverse gradient value D _x And a longitudinal gradient value D _y And further determining the gradient strength and the gradient direction. E.g. according to the transverse gradient D _x And a longitudinal gradient value D _y And calculating the gradient strength D of the point by formula 2, and calculating the gradient direction according to the transverse gradient value, the longitudinal gradient value and formula 3.

Wherein, the horizontal operator sobel _x And vertical operator sobel _y Comprises the following steps:

the following operations are performed on the input image a:

D _x ＝A×sobel _x

D _y ＝A×sobel _y

wherein the gradient strength is calculated by the following formula 2:

the gradient direction is calculated by the following formula 3:

the gradient strength and the gradient direction are calculated according to the method.

In operation S232, an edge region of the card number character is determined from the target region according to the gradient strength, the gradient direction, and the set threshold.

As shown in fig. 6, operation S232 includes operations S2321 to S2323.

In operation 2321, edge points are determined from the target region according to the gradient strength and the gradient direction, the edge points having the maximum gradient strength in the same gradient direction.

After the gradient strength and the gradient direction in the image are determined, traversing all pixel points in the target region, judging whether the current pixel point is the maximum gradient strength with the same gradient direction in the surrounding pixel points, and if so, determining the current pixel point as an edge point.

In operation 2322, the pixels with gradient strength less than the set threshold are deleted.

In an embodiment of the present disclosure, after determining the edge points, the amplitude is non-maxima suppressed in the gradient direction. And adjusting the pixel points in the target area according to the set threshold, judging whether the gradient strength of the pixel points is smaller than the set threshold, and if so, deleting the pixel points with the gradient strength smaller than the set threshold, for example, determining the gray value of the pixel points to be 0.

In operation 2323, the pixel points whose gradient intensities are within the set threshold are filled to determine an edge region of the card number character, where the edge points are located in the edge region.

In the embodiment of the present disclosure, in operation S2322, after the pixel point whose gradient intensity is smaller than the set threshold is deleted, operation S2323 is performed to fill the pixel point located within the set threshold range. For example, the pixel points with gradient intensity greater than the minimum value of the set threshold and less than the maximum value of the set threshold are filled by an 8-pass filling algorithm. For example, a pixel point with the gradient intensity within a set threshold range is used as a seed point, surrounding pixel points are searched in a circulating mode, the pixel with the gradient intensity meeting the set threshold is filled, for example, the gray value is determined to be 255, an edge area is formed after the pixel point is filled, card number characters are arranged in the edge area, and the edge point is located in the edge area.

As shown in fig. 7, after determining the edge region of the card number character in operation S230, performing processing for the edge region to generate a plurality of character images including a single card number character may include operations S233 to S235.

In operation S233, contour detection is performed for the edge region.

The outline of each card number character may be determined, for example, by outline detection of the edge region by an outline detection algorithm.

In operation S234, the outlines of all edge regions are traversed to determine a rectangular outline containing all card number characters of the bank card number.

And performing wheel-base detection on edge areas of all card number characters to determine the outlines of all card number characters, namely determining the rectangular outlines of all card number characters containing the bank card numbers, wherein the rectangular outlines contain all card number characters.

In operation S235, the rectangular outline is divided according to the size of each edge region to generate a plurality of character images containing a single card number character.

In the embodiment of the disclosure, the size of each edge area is counted, and the dividing size of each card number character can be accurately determined by obtaining the counting result. The rectangular outline is divided by the division size, and a plurality of character images containing a single card number character are generated.

For example, the size of the edge area of each character is counted, and for different characters or numbers, the dividing size can be determined according to the total counting result, and the dividing size can divide all the card number characters, so that the situation that a plurality of card number characters are divided together or one card number character is divided into two is avoided, and the identification precision in the identification process is effectively improved.

In operation S240, the character images are input to the trained residual error network for recognition, and a recognition result of the bank card number is generated.

In the embodiment of the present disclosure, after a plurality of character images are acquired, the plurality of character images are input to the residual error network in the order of division for recognition. The ResNet56 residual network can be selected as the residual network, and the ResNet56 residual network has fewer parameters, is simpler in network and shorter in training time, and can solve the problem of poor training effect caused by gradient disappearance or gradient explosion.

In the ResNet56 residual network training process, firstly, a pre-processed training data set is used for training a ResNet56 residual network, and after the data in the training data set are subjected to strengthening, blurring, scaling and the like, more data in the training data set are obtained, so that the ResNet56 residual network obtained through training can accurately identify the bank card number.

In an embodiment of the present disclosure, the average pixel size of the input image of the ResNet56 residual network is 32 × 32 in size. The ResNet56 residual network consists of one input layer, one convolutional layer, and three convolutional large layers and fully-connected layers containing nine residual units. Each convolution large layer comprises nine basic residual error units, each residual error unit comprises two convolution layers, and Relu activation functions are used among the convolution layers to highlight texture features of the image.

A plurality of character images are input as input images to the ResNet56 residual network, and then pass through the first convolutional layer containing 16 convolutional layers with the size of 3 × 3 and the step size of 1, and then 16 feature maps with the size of 32 × 32 are output. The output data after the first convolution layer is 16 × 32 × 32, the output data after the second convolution layer is 32 × 16 × 16, and the output data after the third convolution layer is 64 × 8 × 8. And converting the data output after the third convolution large layer into a characteristic diagram with the size of 1 multiplied by 1 by using a full pooling layer, and then generating a one-dimensional vector through a full connection layer.

And normalizing the output data by using a softmax activation function in an output layer, mapping the data into a certain range, transmitting the data downwards to finish the nonlinear change of the data, enhancing the prediction precision, accurately identifying corresponding numbers or letters according to the input character images, and generating the identification result of the bank card.

Fig. 8 is a block diagram schematically illustrating the structure of the bank card number identification device based on the residual error network according to the embodiment of the disclosure.

As shown in fig. 8, the residual error network-based bank card number identification apparatus 300 of the embodiment of the disclosure includes a first generation module 310, a determination module 320, a second generation module 330, and a third generation module 340.

The first generation module 310 is configured to perform preprocessing on the acquired bank card image to be identified, and generate a preprocessed image. In an embodiment, the first generating module 310 is configured to perform the operation S210 described above, which is not described herein again.

The determining module 320 is configured to determine a target area from the preprocessed image based on a preset rule, wherein the target area is associated with the type of the bank card, and the bank card number of the bank card to be identified is located in the target area. In an embodiment, the determining module 320 is configured to perform the operation S220 described above, which is not described herein again.

The second generating module 330 is configured to determine an edge region containing the card number characters from the target region by an edge detection algorithm, and process the edge region to generate a plurality of character images containing a single card number character. In an embodiment, the second generating module 330 is configured to perform the operation S230 described above, which is not described herein again.

The third generating module 340 is configured to input the plurality of character images to the trained residual error network for recognition, and generate a recognition result of the bank card number. In an embodiment, the third generating module 340 is configured to perform the operation S240 described above, which is not described herein again.

In some exemplary embodiments of the present disclosure, the first generation module includes a first generation submodule configured to: carrying out correction processing on the acquired bank card image to be identified; carrying out gray level processing on the image subjected to the correction processing to obtain a gray level image; and denoising the gray level image to generate a preprocessed image.

In some exemplary embodiments of the present disclosure, the determining module includes a determining submodule configured to: acquiring at least one set area of the preprocessed image according to a preset rule, wherein the set area is associated with the type of the bank card; detecting whether at least one set area has characters; and determining the set area with the characters as a target area, wherein the bank card number of the bank card type associated with the target area is positioned in the target area.

In some exemplary embodiments of the present disclosure, the second generating module includes a first generating unit and a second generating unit, the first generating unit is configured to: traversing pixels of the target area through an edge detection algorithm, and determining the gradient intensity and the gradient direction of the pixels; and determining the edge area of the card number characters from the target area according to the gradient strength, the gradient direction and the set threshold value.

In some exemplary embodiments of the present disclosure, the first generating unit includes a first generating subunit configured to: determining edge points from the target area according to the gradient strength and the gradient direction, wherein the edge points have the maximum gradient strength in the same gradient direction; deleting the pixel points with the gradient intensity smaller than a set threshold; and filling the pixel points with the gradient intensity within the set threshold value to determine the edge area of the card number character, wherein the edge points are located in the edge area.

According to the embodiment of the present disclosure, any plurality of the first generation module 310, the determination module 320, the second generation module 330, the third generation module 340, the first generation sub-module, the determination sub-module, the first generation unit, the second generation unit, and the first generation sub-unit may be combined and implemented in one module, or any one of them may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first generation module 310, the determination module 320, the second generation module 330, the third generation module 340, the first generation sub-module, the determination sub-module, the first generation unit, the second generation unit, and the first generation sub-unit may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or any other reasonable manner of integrating or packaging a circuit, etc., or as any one of three implementations of software, hardware, and firmware, or as a suitable combination of any of them. Alternatively, at least one of the first generation module 310, the determination module 320, the second generation module 330, the third generation module 340, the first generation sub-module, the determination sub-module, the first generation unit, the second generation unit and the first generation sub-unit may be at least partly implemented as a computer program module, which when executed may perform a corresponding function.

Fig. 9 schematically shows a block diagram of an electronic device adapted to implement a residual error network-based bank card number identification method according to an embodiment of the present disclosure. The electronic device shown in fig. 9 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 9, an electronic device 400 according to an embodiment of the present disclosure includes a processor 401 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. Processor 401 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 401 may also include onboard memory for caching purposes. Processor 401 may include a single processing unit or multiple processing units for performing the different actions of the method flows in accordance with embodiments of the present disclosure.

In the RAM 403, various programs and data necessary for the operation of the electronic apparatus 400 are stored. The processor 401, ROM 402 and RAM 403 are connected to each other by a bus 404. The processor 401 performs various operations of the method flows according to the embodiments of the present disclosure by executing programs in the ROM 402 and/or the RAM 403. Note that the programs may also be stored in one or more memories other than the ROM 402 and RAM 403. The processor 401 may also perform various operations of the method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, electronic device 400 may also include an input/output (I/O) interface 405, input/output (I/O) interface 405 also being connected to bus 404. Electronic device 400 may also include one or more of the following components connected to I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including a display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. A driver 410 is also connected to the I/O interface 405 as needed. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 410 as needed, so that a computer program read out therefrom is mounted in the storage section 408 as needed.

The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement a residual error network-based bank card number identification method according to an embodiment of the disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include ROM 402 and/or RAM 403 and/or one or more memories other than ROM 402 and RAM 403 described above.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the method illustrated in the flow chart. When the computer program product runs in a computer system, the program code is used for causing the computer system to realize the bank card number identification method based on the residual error network provided by the embodiment of the disclosure.

The computer program performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure when executed by the processor 401. The above described systems, devices, modules, units, etc. may be implemented by computer program modules according to embodiments of the present disclosure.

In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of a signal on a network medium, downloaded and installed through the communication section 409, and/or installed from the removable medium 411. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 409, and/or installed from the removable medium 411. The computer program, when executed by the processor 401, performs the above-described functions defined in the system of the embodiments of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user computing device, partly on the user device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.

The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.

Claims

1. A bank card number identification method based on a residual error network comprises the following steps:

preprocessing the acquired bank card image to be identified to generate a preprocessed image;

determining a target area from the preprocessed image based on a preset rule, wherein the target area is associated with the type of the bank card, and the bank card number of the bank card to be identified is located in the target area;

determining an edge area containing the card number characters from the target area through an edge detection algorithm, processing the edge area, and generating a plurality of character images containing single card number characters;

and inputting the character images into the trained residual error network for recognition to generate a recognition result of the bank card number.

2. The method according to claim 1, wherein the preprocessing is performed on the acquired bank card image to be identified, and the generating of the preprocessed image comprises:

carrying out correction processing on the acquired bank card image to be identified;

carrying out gray level processing on the image subjected to the positive conversion processing to obtain a gray level image;

and denoising the gray level image to generate a preprocessed image.

3. The method of claim 2, wherein the determining a target region from the pre-processed image based on a preset rule comprises:

acquiring at least one set area of a preprocessed image according to the preset rule, wherein the set area is associated with the type of the bank card;

detecting whether characters exist in the at least one set area;

and determining the set area with the characters as a target area, wherein the bank card number of the bank card type associated with the target area is positioned in the target area.

4. The method of claim 1, wherein said determining an edge region containing card number characters from the target region by an edge detection algorithm comprises:

traversing the pixels of the target area through an edge detection algorithm, and determining the gradient intensity and the gradient direction of the pixels;

and determining the edge area of the card number characters from the target area according to the gradient strength, the gradient direction and the set threshold value.

5. The method of claim 4, wherein said determining an edge region of a card number character from the target region based on the gradient strength, gradient direction, and a set threshold comprises:

determining an edge point from the target area according to the gradient strength and the gradient direction, wherein the edge point has the maximum gradient strength in the same gradient direction;

deleting the pixel points with the gradient intensity smaller than the set threshold;

and filling the pixel points with the gradient strength within the set threshold value to determine the edge area of the card number character, wherein the edge points are located in the edge area.

6. The method of claim 5, wherein said processing for said edge region to generate a plurality of character images containing a single card number character comprises:

carrying out contour detection on the edge area;

traversing the outlines of all the edge areas, and determining rectangular outlines containing all the card number characters of the bank card number;

and dividing the rectangular outline according to the size of each edge area to generate a plurality of character images containing single card number characters.

7. The method of claim 1, wherein the residual network comprises a ResNet56 residual network.

8. A bank card number identification device based on a residual error network, comprising:

the first generation module is configured to preprocess the acquired bank card image to be identified and generate a preprocessed image;

the determining module is configured to determine a target area from the preprocessed image based on a preset rule, wherein the target area is associated with the type of the bank card, and the bank card number of the bank card to be identified is located in the target area;

the second generation module is configured to determine an edge area containing the card number characters from the target area through an edge detection algorithm, process the edge area and generate a plurality of character images containing a single card number character;

and the third generation module is configured to input the character images to the trained residual error network for recognition, and generate a recognition result of the bank card number.

9. An electronic device, comprising:

one or more processors;

storage means for storing executable instructions that, when executed by the processor, implement the method of any one of claims 1 to 7.

10. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, implement the method of any one of claims 1 to 7.

11. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.