CN112801165B - Card review method and device - Google Patents

Abstract

The embodiment of the invention provides a card auditing method and device, wherein the method comprises the following steps: the method comprises the steps of obtaining characteristic information of each element in an image to be detected, wherein the image to be detected is obtained by collecting an image of a card to be checked or a card surface design image of the card to be checked provided by a sender, the characteristic information comprises size information and position information, constructing a standard image corresponding to the card type of the card to be checked, and determining checking results of the card to be checked according to the characteristic information of each element in the standard image and the characteristic information of each element in the image to be detected.

Description

Card review method and device

Technical field

This application relates to the technical field of card auditing, and in particular to a card auditing method and device.

Background technique

With the development and maturity of the bank card industry, various forms of physical card designs emerge in endlessly. In the current promotion process, the card design submitted by each card-issuing bank is mainly reviewed through manual review, but the efficiency of manual review is low.

In order to improve the efficiency of review, the machine vision algorithms that may be used at present mainly identify semantic information such as card numbers and text of bank cards, but what about non-semantic information such as the size information of bank cards and the standard position information of each element on the card surface? Identification is not involved.

Therefore, there is an urgent need for a card review method that can review non-semantic information on cards.

Contents of the invention

Embodiments of the present invention provide a card review method and device, which can review non-semantic information on cards and improve the accuracy of card review.

In a first aspect, an embodiment of the present invention provides a card review method, which method includes:

Obtain the characteristic information of each element in the image to be detected; the image to be detected is obtained by collecting the image of the card to be audited or based on the card surface design image of the card to be audited provided by the party submitting the inspection; the characteristic information includes size information and position information;

Construct a standard image corresponding to the card type of the card to be reviewed;

Based on the characteristic information of each element in the standard image and the characteristic information of each element in the image to be detected, the audit result of the card to be audited is determined.

In the above method, the characteristic information of each element in the image to be detected is obtained, where the characteristic information includes size information and position information, a standard image corresponding to the card type of the card to be reviewed is constructed, and then based on the characteristic information of each element in the standard image and the information to be detected The characteristic information of each element in the image determines the audit result of the card to be audited, so that non-semantic information such as size information and position information of the card to be audited can be audited, which helps to improve the accuracy of the audit.

Optionally, build standard images corresponding to the types of cards to be reviewed, including:

Obtain the element image of the first element of each template from N templates included in the template library; the N is an integer greater than 1;

For the element image of the first element of each template in N templates, execute: match the element image with the image to be detected, and obtain the first area in the image to be detected that has the highest matching degree with the element image; each template corresponds to one The first area, each first area corresponds to a matching value;

Determine the first area with the largest matching value from the N first areas;

Using the first area with the largest matching value as the positioning anchor point, a standard image corresponding to the type of card to be reviewed is constructed based on the type of card to be reviewed and the feature information of the first area with the largest matching value.

In the above method, the position information and size information of the first element in the template of each card type are fixed. By matching the element image of the first element in the template with the image to be detected, the element in the image to be detected can be accurately positioned. The position of the first element is used to construct a standard image suitable for verifying the detection data of the card to be reviewed, which helps to improve the accuracy of the review.

Optionally, match the element image with the image to be detected to obtain the first region in the image to be detected that has the highest matching degree with the element image, including:

Use the minimum circumscribed rectangle of the element image as a sliding window, traverse all areas in the image to be detected, and obtain the area with the highest degree of matching with the feature information of the minimum circumscribed rectangle;

The area with the highest degree of matching with the feature information of the smallest circumscribed rectangle is determined as the first area with the highest degree of matching with the element image in the image to be detected.

In the above method, the smallest circumscribed rectangle of the element image is used as a sliding window to traverse all areas in the image to be detected, and the area in the image to be detected that matches the element image with the highest degree can be quickly obtained.

Optionally, obtain the characteristic information of each element in the image to be detected, including:

Process the image to be detected to obtain a grayscale image;

Determine the characteristic information of the block area in the image to be detected based on the grayscale value of each pixel along the long axis direction and the grayscale value of each pixel along the short axis direction in the grayscale image;

Detect the contour lines in the image to be detected and obtain the characteristic information of the contour lines of the card to be reviewed.

In the above method, each element in the image to be detected is mainly block-shaped areas and contour lines. By detecting block-shaped areas and contour lines, the characteristic information of each element in the image to be detected can be accurately obtained.

Optionally, determining the audit result of the card to be audited according to the feature information of each element in the standard image and the feature information of each element in the image to be detected includes:

For each element in the standard image, do:

Determine the proportional deviation of the elements based on the size information of the elements in the standard image and the size information of the elements in the image to be detected;

Determine the position deviation of the element based on the position information of the element in the standard image and the position information of the element in the image to be detected;

Based on the proportion deviation of each element and the position deviation of each element, the review result of the card to be reviewed is determined.

In the above method, by determining the proportion deviation of each element and the position deviation of each element, the review result of the card to be reviewed can be determined in a quantitative manner.

Optionally, determine the review result of the card to be reviewed based on the proportion deviation of each element and the position deviation of each element, including:

If the proportion deviation of each element is less than the first threshold, and the position deviation of each element is less than the second threshold, it is determined that the card to be reviewed passes the review.

Optionally, determine the review result of the card to be reviewed based on the proportion deviation of each element and the position deviation of each element, including:

According to the deviation of each element and the weight coefficient corresponding to each element, the total deviation between the image to be detected and the standard image is determined;

If the total deviation is less than the third threshold, it is determined that the card to be reviewed passes the review.

In a second aspect, an embodiment of the present invention provides a card verification device, which includes:

The acquisition module is used to obtain the characteristic information of each element in the image to be detected; the image to be detected is obtained by collecting the image of the card to be audited or based on the card surface design image of the card to be audited provided by the party submitting the inspection; the characteristic information Includes size information and location information;

A building module used to build a standard image corresponding to the type of card to be reviewed;

A determination module, configured to determine the review result of the card to be reviewed based on the feature information of each element in the standard image and the feature information of each element in the image to be detected.

In a third aspect, embodiments of the present application further provide a computing device, including: a memory for storing a program; a processor for calling the program stored in the memory, and executing various methods of the first aspect according to the obtained program. The approach described in Possible Designs.

In a fourth aspect, embodiments of the present application also provide a computer-readable non-volatile storage medium, including a computer-readable program. When the computer reads and executes the computer-readable program, the computer is caused to execute the steps of the first aspect. Various possible designs are described in the approach.

These implementations or other implementations of the present application will be more concise and understandable in the description of the following embodiments.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings needed to describe the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. Those of ordinary skill in the art can also obtain other drawings based on these drawings without exerting any creative effort.

Figure 1 is a schematic flow chart of a card review method provided by an embodiment of the present invention;

Figure 2 is a schematic diagram of the minimum circumscribed rectangle provided by the embodiment of the present invention;

Figure 3 is a schematic diagram of the bank card standard construction in the rectangular coordinate system provided by the embodiment of the present invention;

Figure 4 is a schematic diagram of the bank card provided by the embodiment of the present invention in a rectangular coordinate system;

Figure 5 is a schematic diagram of the histogram detection results provided by the embodiment of the present invention;

Figure 6 is a schematic diagram of a straight line to be measured provided by an embodiment of the present invention;

Figure 7 is a schematic diagram of the Hough transform provided by an embodiment of the present invention;

Figure 8 is a schematic diagram of the outline of a card provided by an embodiment of the present invention;

Figure 9 is a schematic diagram of a card verification device provided by an embodiment of the present invention.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

The word "exemplary" as used below means "serving as an example, example, or illustrative." Any embodiment described as "exemplary" is not necessarily to be construed as superior or superior to other embodiments.

The terms "first" and "second" in this article are only used for descriptive purposes and cannot be understood to express or imply relative importance or implicitly indicate the number of indicated technical features. Therefore, the features defined as “first” and “second” may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, unless otherwise specified, “plurality” The meaning is two or more. Furthermore, the term "includes" and any variations thereof are intended to cover non-exclusive protection. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes Other steps or units inherent to such processes, methods, products or devices.

Some terms used in the embodiments of the present invention are explained below to facilitate understanding by those skilled in the art.

Minimum circumscribed rectangle: refers to the maximum range of several two-dimensional shapes (such as points, lines, polygons) represented by two-dimensional coordinates, that is, the maximum abscissa, minimum abscissa, and maximum vertical coordinate of each vertex of a given two-dimensional shape. The coordinates and the minimum vertical coordinate determine the rectangle of the lower boundary. Such a rectangle contains the given two-dimensional shape with sides parallel to the coordinate axes. The minimum bounding rectangle is the two-dimensional form of the minimum bounding box.

Pixel point: refers to the smallest unit in an image represented by a sequence of numbers, also called a pixel. A pixel is an indivisible unit or element of the entire image. Each bitmap image contains a certain number of pixels, which determine the size of the image on the screen. A picture is composed of many pixels. For example, the picture size is 500×338, which means that the picture is composed of a 500×338 pixel matrix. The width of this picture is 500 pixels in length and the height is 338 pixels in length. A total of 500×338 =149000 pixels. Put the mouse on an image, and the size and size will be displayed. The size here is pixels.

In order to solve the technical problems in related technologies, embodiments of the present invention provide a card verification method and device. The card review method provided by the embodiment of the present invention can be applied to bank card identification scenarios, newly designed bank card review scenarios, etc.

Figure 1 shows a flow chart of a card review method provided by an embodiment of the present invention. The card review method can be executed by a card review device, as shown in Figure 1. The method includes the following steps:

Step 101: Obtain feature information of each element in the image to be detected.

Here, the image to be detected is obtained by collecting the image of the card to be audited or based on the card surface design image of the card to be audited provided by the party submitting the inspection. In the specific implementation, the image of either front or back of the card to be audited can be collected. The obtained image can also be obtained by collecting images of the front and back sides.

In the embodiment of the present invention, the cards to be reviewed may include but are not limited to bank cards, shopping cards, etc. The following description takes the card to be reviewed as a bank card as an example. For example, the bank card includes but is not limited to the following elements: chip, magnetic stripe, card number, name, card validity period, UnionPay logo, name of the issuing bank, card outline, etc.

In step 101, the feature information includes size information and position information. The image to be detected is placed under the rectangular coordinate system XOY. The position information of the element can be expressed by the position coordinates of the element on the image to be detected. For example, Detects the coordinate representation of the upper left corner on the image. The size information of an element can be expressed by the length of the element on the X-axis and the length on the Y-axis.

If the shape of the element is not a rectangle, for example, the element is a rounded rectangle, or if the element is a parallelogram, in this case, the position information and size information of the element's smallest enclosing rectangle can be used as the element's feature information. Taking the element as the UnionPay logo as an example, as shown in Figure 2, the location information of the UnionPay logo can be represented by the coordinates (x, y) of point A in the upper left corner of the smallest external rectangle of the UnionPay logo (the dotted rectangular box in Figure 2). The size information of the element can be expressed by the width of the X-axis and the length of the Y-axis of the UnionPay logo's smallest enclosing rectangle (the dotted rectangle in Figure 2). In this example, the characteristic information of the UnionPay logo can be expressed as [(x,y),width,height].

Step 102: Construct a standard image corresponding to the card type of the card to be reviewed.

Step 103: Determine the review result of the card to be reviewed based on the feature information of each element in the standard image and the feature information of each element in the image to be detected.

It should be noted that the above-mentioned step 101 and step 102 may be in no particular order. Step 101 may precede step 102, or step 101 may precede step 102.

In the above method, the characteristic information of each element in the image to be detected is obtained, where the characteristic information includes size information and position information, a standard image corresponding to the card type of the card to be reviewed is constructed, and then based on the characteristic information of each element in the standard image and the information to be detected The characteristic information of each element in the image determines the audit result of the card to be audited, so that non-semantic information such as size information and position information of the card to be audited can be audited, which helps to improve the accuracy of the audit.

In a specific implementation, a template library is stored in the card review device. The template library can include templates of multiple card types. Each card type corresponds to at least one template. For example, the template library includes N templates, where N is greater than 1. integer. Each template includes standards for the position and size of each element, and standard images corresponding to the corresponding card types can be produced based on the template.

In the above step 102, constructing a standard image corresponding to the type of card to be reviewed includes: obtaining the element image of the first element of each template from N templates included in the template library; targeting the first element of each template in the N templates Element image of the element, execution: match the element image with the image to be detected, and obtain the first area in the image to be detected that has the highest matching degree with the element image; each template corresponds to a first area, and each first area corresponds to a Match value. Determine the first area with the largest matching value from the N first areas; use the first area with the largest matching value as the positioning anchor point, and construct a A standard image corresponding to the type of card to be reviewed.

In the embodiment of this application, the first element may be an element whose position information and size information are relatively fixed selected from the templates of each card type, such as the UnionPay logo on a bank card.

In the specific implementation, taking the first element as the UnionPay logo as an example, the UnionPay logo image can be obtained by intercepting the image from an existing standard logo image, for example, naming it Image1, and selecting the resolution as 600*800. At the same time, the interpolation method of the image pyramid (such as Gaussian pyramid) can be used to scale Image1 to match each area in the image to be detected in the size dimension. The multiples are 1/4 times, 1 times, and 4 times respectively. . Since the Gaussian kernel is a linear kernel, using Gaussian pyramid to blur the image will not introduce other noise. In some other embodiments, a linear interpolation method can be used, which can increase the calculation speed compared to the image pyramid difference method.

In an example, take the image to be detected as a bank card image, the element image of the first element as the UnionPay logo image, and the N value as 10 as an example, and obtain the UnionPay logo from each of the 10 templates. image, so that you can obtain N UnionPay logo images corresponding to template 1, UnionPay logo image corresponding to template 2,..., UnionPay logo image corresponding to template N, etc., and combine each UnionPay logo image with the bank card image. For matching, take the matching of the UnionPay logo image corresponding to template 1 and the bank card image as an example to illustrate. There are multiple areas in the bank card image. The UnionPay logo image corresponding to template 1 is matched with all areas on the bank card image. From From the matching results, the area with the highest degree of matching with the UnionPay logo image corresponding to template 1 is determined, that is, the first area. At the same time, the matching value of the UnionPay logo image corresponding to template 1 and the first area is obtained. By analogy, the first region with the highest degree of matching with the UnionPay logo image corresponding to template n is obtained, as well as the matching value between the UnionPay logo image corresponding to template n and the first region, where n ranges from 2 to 10. The first area with the largest matching value is determined from the obtained 10 first areas. The first area with the largest matching value can be regarded as the area where the first element in the image to be detected is located. Then, the first area with the largest matching value is used as the positioning anchor point, and based on the type of card to be reviewed and the feature information of the first area with the largest matching value, a standard image corresponding to the type of card to be reviewed is constructed.

In the above method, by matching the element image of the first element in the template with the image to be detected, the position of the first element in the image to be detected can be accurately located, thereby constructing a standard suitable for verifying the detection data of the card to be reviewed. Images to help improve review accuracy.

Based on the above embodiment, matching the element image with the image to be detected to obtain the first area in the image to be detected that has the highest matching degree with the element image includes: using the smallest circumscribed rectangle of the element image as a sliding window, traversing the image to be detected of all areas, the area with the highest degree of matching with the feature information of the minimum circumscribed rectangle is obtained; the area with the highest degree of matching with the feature information of the minimum circumscribed rectangle is determined as the first area in the image to be detected that has the highest degree of matching with the element image.

For example, the first element is the UnionPay logo, the element image is the UnionPay logo image, and the minimum circumscribed rectangle of the UnionPay logo image is traversed on the bank card image as a sliding window, and the area with the highest degree of matching with the minimum circumscribed rectangle can be obtained. The minimum circumscribed rectangle Taking the dotted rectangular box in Figure 2 as an example, the first area can be the area where the UnionPay logo in Figure 2 is located. Then, use the type of card to be reviewed, the coordinate information (x, y) of point A, and the size information [width, height] to determine the coordinates and size information of the standard image that the type of card to be reviewed needs to meet. As shown in Figure 3, the first area is used as the positioning anchor point, that is, the UnionPay logo is used as the positioning anchor point. According to the coordinates and size information of the standard image that needs to be achieved, each element of the bank card is reconstructed, thereby constructing the card to be reviewed. The standard image corresponding to the type.

In the above method, the smallest circumscribed rectangle of the element image is used as a sliding window to traverse all areas in the image to be detected, and the area in the image to be detected that matches the element image with the highest degree can be quickly obtained.

During the specific implementation process, in step 102, the characteristic information of each element in the image to be detected is obtained, including: processing the image to be detected to obtain a grayscale image; according to the grayscale of each pixel along the long axis direction in the grayscale image value and the gray value of each pixel along the short axis direction to determine the characteristic information of the block area in the image to be detected; detect the contour line in the image to be detected and obtain the characteristic information of the contour line of the card to be reviewed.

The processing of the image to be detected may include grayscale processing of the image to be detected to obtain a grayscale image. Optionally, Gaussian filtering can also be performed on the image to be detected in order to remove some interfering pixels in the image to be detected.

Then, the histogram detection method can be used to detect blocky areas. Taking the image to be detected as a bank card image as an example, as shown in Figure 4, the bank card image is placed under the rectangular coordinate system XOY. The long axis direction can be the X axis direction in Figure 4, and the short axis direction can be Y-axis direction in Figure 4. It should be noted that the length of the bank card in the X-axis direction can be regarded as the width mentioned above, and the length of the bank card in the Y-axis direction can be regarded as the height mentioned above.

Draw the curve of the Sum function of the sum of the pixel values of each pixel point in the Y-axis direction of the bank card image. The histogram detection result shown in Figure 5 is the sum function of the Sum function of the sum of the pixel values of each pixel point in the Y-axis direction. curve, the value on the X-axis in Figure 5 represents the size range of the bank card image in Figure 4 along the Y-axis direction, 0-260, and the value on the Y-axis in Figure 5 represents the grayscale value corresponding to any value in the size range. and. From Figure 5, the starting point and end point of the peak value are projected onto the X-axis, and the position and height value of the bank card magnetic stripe on the Y-axis in Figure 4 can be determined.

Similarly, draw the curve of the Sum function of the sum of pixel values of each pixel of the bank card image in the X-axis direction, and then determine the position and width value of the bank card magnetic stripe on the x-axis in Figure 4.

Through the above example, the characteristic information of the block area of the image to be detected can be obtained.

For the size of the bank card, the Hough line detection method can be used to determine the size. The Hough transform algorithm uses a voting algorithm to find targets with specific shapes in the image. The Hough transform algorithm calculates the local maximum value of the cumulative result in a parameter space to obtain a set that conforms to the specific shape as the Hough transform result. When it is necessary to detect straight lines, in order to generally represent all straight lines, the polar coordinate system is used, so that each point on the polar coordinate system represents a series of sinusoids with different initial phases, amplitudes, and the same period. All sinusoids The intersection point will represent this straight line in x-y space. For example, after Hough transforming the white straight line in Figure 6, the image shown in Figure 7 is obtained, and the intersection point is the white straight line calibrated in Figure 6.

As shown in Figure 8, after using the Hough transform algorithm to detect the straight line outline of the bank card, we extend the longest straight line to obtain the intersection point, and use the coordinate position of the intersection point to confirm the position information.

Through the above method, it is possible to complete the measurement of regular graphics on the image to be detected, such as the size of the card, the chip, the magnetic stripe, and the contour line, and obtain the characteristic information of each element of the real card to be reviewed.

In the above method, each element in the image to be detected is mainly block-shaped areas and contour lines. By detecting block-shaped areas and contour lines, the characteristic information of each element in the image to be detected can be accurately obtained.

During the specific implementation process, in step 103, the audit result of the card to be audited is determined based on the characteristic information of each element in the standard image and the characteristic information of each element in the image to be detected, including: for each element in the standard image, execute: According to the size information of the elements in the standard image and the size information of the elements in the image to be detected, the proportion deviation of the elements is determined; according to the position information of the elements in the standard image and the position information of the elements in the image to be detected, the position deviation of the elements is determined; according to each The proportion deviation of elements and the position deviation of each element determine the review result of the card to be reviewed.

In the above method, by determining the proportion deviation of each element and the position deviation of each element, the review result of the card to be reviewed can be determined in a quantitative manner.

Based on the above embodiments, there are multiple implementation methods for determining the audit result of the card to be audited based on the proportion deviation of each element and the position deviation of each element.

As a possible implementation, if the proportional deviation of each element is less than the first threshold, and the position deviation of each element is less than the second threshold, it is determined that the card to be reviewed passes the review. If the proportion deviation of each element is greater than or equal to the first threshold, or the position deviation of each element is greater than or equal to the second threshold, it is determined that the card to be reviewed has failed the review.

For example, the coordinate deviation of each element is measured in the form of a minimum circumscribed rectangle. The corresponding feature information of each element in the image to be detected is [(x, y), w, h], and the corresponding feature information of each element in the standard image is The feature information is [(X,Y),W,H]. The calculation of the deviation value between the two mainly includes two parts, the deviation of the size center point (that is, the coordinate point of the upper left corner of the minimum circumscribed rectangle) and the deviation of the size ratio. Among them, the deviation of the center point is directly based on the Manhattan distance, and the deviation of the size ratio is the average of the differences between the two.

The deviation of each element is defined as: position deviation and proportional deviation, where the positional deviation is |x-X|, |y-Y|, and the proportional deviation is w/h–W/H. If any of the three deviation values |x-X|, |y-Y|, w/h–W/H is greater than 0, the deviation value P is set to 0, otherwise it is set to 1, thereby ensuring that the deviation value P in the figure is Verification feedback can be obtained when the position and proportion of elements deviate.

As another possible implementation method, the total deviation between the image to be detected and the standard image is determined based on the deviation of each element and the weight coefficient corresponding to each element; if the total deviation is less than the third threshold, it is determined that the card to be reviewed passes the review. If the total deviation is greater than or equal to the third threshold, it is determined that the card to be reviewed has failed the review.

Taking the image to be detected as an example, including four elements such as area chip, logo area, card size, and card size, these four elements are configured with different weights according to different card types. As an example, depending on the card type, the value of w can be 0 and 1. If the current card type is designed with this element, it is set to 1, otherwise it is set to 0.

For example, the deviations of the four elements are set as: chip area deviation P1, Logo area deviation P2, card size deviation P3 and card size deviation P4. The corresponding weights of the four elements are w_1, w_2, w_3, w_4, respectively. The total deviation is calculated as P=w_1*P1+w_2*P2+w_3*P3+w_4*P4.

In the above method, by determining the proportion deviation of each element and the position deviation of each element, the review result of the card to be reviewed can be determined in a quantitative manner.

The following are device embodiments of the present invention. For details that are not described in detail in the device embodiments, please refer to the above one-to-one corresponding method embodiments.

Based on the same concept, an embodiment of the present invention provides a card verification device. Figure 9 is a schematic diagram of a card verification device provided by an embodiment of the present application. As shown in Figure 9, it includes:

The acquisition module 901 is used to acquire the characteristic information of each element in the image to be detected; the image to be detected is an image of the card to be reviewed or is obtained based on the card surface design image of the card to be reviewed provided by the inspection party; the characteristic information includes size information and position information;

Building module 902, used to build a standard image corresponding to the card type of the card to be reviewed;

The determination module 903 is used to determine the audit result of the card to be audited based on the characteristic information of each element in the standard image and the characteristic information of each element in the image to be detected.

Optional, building module 902, specifically used for:

Obtain the element image of the first element of each template from the N templates included in the template library; N is an integer greater than 1;

For the element image of the first element of each template in N templates, execute: match the element image with the image to be detected, and obtain the first area in the image to be detected that has the highest matching degree with the element image; each template corresponds to one The first area, each first area corresponds to a matching value;

Determine the first area with the largest matching value from the N first areas;

Using the first area with the largest matching value as the positioning anchor point, a standard image corresponding to the type of card to be reviewed is constructed based on the type of card to be reviewed and the feature information of the first area with the largest matching value.

Optionally, the building module 902 is specifically used to: use the minimum circumscribed rectangle of the element image as a sliding window, traverse all areas in the image to be detected, and obtain the area with the highest degree of matching with the feature information of the minimum circumscribed rectangle;

The area with the highest degree of matching with the feature information of the smallest circumscribed rectangle is determined as the first area with the highest degree of matching with the element image in the image to be detected.

Optional, obtain module 901, specifically used for:

Process the image to be detected to obtain a grayscale image;

Determine the characteristic information of the block area in the image to be detected based on the grayscale value of each pixel along the long axis direction and the grayscale value of each pixel along the short axis direction in the grayscale image;

Detect the contour lines in the image to be detected and obtain the characteristic information of the contour lines of the card to be reviewed.

Optional, determine module 903, specifically used for:

For each element in the standard image, do:

Determine the proportional deviation of the elements based on the size information of the elements in the standard image and the size information of the elements in the image to be detected;

Determine the position deviation of the element based on the position information of the element in the standard image and the position information of the element in the image to be detected;

Based on the proportion deviation of each element and the position deviation of each element, the review result of the card to be reviewed is determined.

Optional, determine module 903, specifically used for:

If the proportion deviation of each element is less than the first threshold, and the position deviation of each element is less than the second threshold, it is determined that the card to be reviewed passes the review.

Optional, determine module 903, specifically used for:

According to the deviation of each element and the weight coefficient corresponding to each element, the total deviation between the image to be detected and the standard image is determined;

If the total deviation is less than the third threshold, it is determined that the card to be reviewed passes the review.

Those skilled in the art will understand that embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment that combines software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the present application. It will be understood that each process and/or block in the flowchart illustrations and/or block diagrams, and combinations of processes and/or blocks in the flowchart illustrations 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 device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce a use A device for realizing the functions specified in one process or multiple processes of the flowchart and/or one block or multiple blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory that causes a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction means, the instructions The device implements the functions specified in a process or processes of the flowchart and/or a block or blocks of the block diagram.

These computer program instructions may also be loaded onto a computer or other programmable data processing device, causing a series of operating steps to be performed on the computer or other programmable device to produce computer-implemented processing, thereby executing on the computer or other programmable device. Instructions provide steps for implementing the functions specified in a process or processes of a flowchart diagram and/or a block or blocks of a block diagram.

Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. In this way, if these modifications and variations of the present application fall within the scope of the claims of the present application and equivalent technologies, the present application is also intended to include these modifications and variations.

Claims (9)

1. A method of card auditing, comprising:

acquiring characteristic information of each element in an image to be detected; the image to be detected is obtained by collecting an image of the card to be checked or a card surface design image of the card to be checked provided by a sender; the characteristic information comprises size information and position information;

constructing a standard image corresponding to the card type of the card to be checked;

determining an auditing result of the card to be audited according to the characteristic information of each element in the standard image and the characteristic information of each element in the image to be detected;

the construction of the standard image corresponding to the type of the card to be audited comprises the following steps:

acquiring element images of a first element of each template from N templates included in a template library; the N is an integer greater than 1;

for the element image of the first element of each of the N templates, performing: matching the element image with the image to be detected to obtain a first area with highest matching degree with the element image in the image to be detected; each template corresponds to a first area, and each first area corresponds to a matching value;

determining a first region with the largest matching value from N first regions;

and constructing a standard image corresponding to the type of the card to be checked according to the type of the card to be checked and the characteristic information of the first area with the largest matching value by taking the first area with the largest matching value as a positioning anchor point.

2. The method according to claim 1, wherein the matching the element image with the image to be detected to obtain a first region with the highest matching degree with the element image in the image to be detected includes:

traversing all areas in the image to be detected by taking the minimum circumscribed rectangle of the element image as a sliding window to obtain an area with highest matching degree with the characteristic information of the minimum circumscribed rectangle;

and determining the region with the highest matching degree with the feature information of the minimum circumscribed rectangle as a first region with the highest matching degree with the element image in the image to be detected.

3. The method according to any one of claims 1-2, wherein the acquiring feature information of each element in the image to be detected includes:

processing the image to be detected to obtain a gray image;

determining characteristic information of a block area in the image to be detected according to the gray value of each pixel point in the long axis direction and the gray value of each pixel point in the short axis direction in the gray image;

and detecting the contour lines in the image to be detected to obtain the characteristic information of the contour lines of the card to be checked.

4. A method according to claim 3, wherein determining the result of the verification of the card to be verified based on the feature information of each element in the standard image and the feature information of each element in the image to be detected comprises:

for each element in the standard image, performing:

determining the proportion deviation of the elements according to the size information of the elements in the standard image and the size information of the elements in the image to be detected;

determining the position deviation of the element according to the position information of the element in the standard image and the position information of the element in the image to be detected;

and determining the auditing result of the card to be audited according to the proportion deviation of each element and the position deviation of each element.

5. The method of claim 4, wherein said determining the audit result of said card to be audited based on the ratio deviation of each of said elements and the position deviation of each of said elements comprises:

and if the proportion deviation of each element is smaller than a first threshold value and the position deviation of each element is smaller than a second threshold value, determining that the card to be checked passes the checking.

6. The method of claim 4, wherein said determining the audit result of said card to be audited based on the ratio deviation of each of said elements and the position deviation of each of said elements comprises:

determining the total deviation of the image to be detected and the standard image according to the deviation of each element and the weight coefficient corresponding to each element;

and if the total deviation is smaller than a third threshold value, determining that the card to be checked passes the check.

7. A card auditing device, comprising:

the acquisition module is used for acquiring the characteristic information of each element in the image to be detected; the image to be detected is obtained by collecting an image of the card to be checked or a card surface design image of the card to be checked provided by a sender; the characteristic information comprises size information and position information;

the construction module is used for constructing a standard image corresponding to the card type of the card to be checked;

the determining module is used for determining the auditing result of the card to be audited according to the characteristic information of each element in the standard image and the characteristic information of each element in the image to be detected;

the construction of the standard image corresponding to the type of the card to be audited comprises the following steps:

acquiring element images of a first element of each template from N templates included in a template library; the N is an integer greater than 1;

for the element image of the first element of each of the N templates, performing: matching the element image with the image to be detected to obtain a first area with highest matching degree with the element image in the image to be detected; each template corresponds to a first area, and each first area corresponds to a matching value;

determining a first region with the largest matching value from N first regions;

and constructing a standard image corresponding to the type of the card to be checked according to the type of the card to be checked and the characteristic information of the first area with the largest matching value by taking the first area with the largest matching value as a positioning anchor point.

8. A computer readable storage medium, characterized in that the computer readable storage medium stores a program which, when run on a computer, causes the computer to implement the method of any one of claims 1 to 6.

9. A computer device, comprising:

a memory for storing a computer program;

a processor for invoking a computer program stored in said memory, performing the method according to any of claims 1 to 6 in accordance with the obtained program.