WO2018010391A1

WO2018010391A1 - Board inspection method and device

Info

Publication number: WO2018010391A1
Application number: PCT/CN2016/113235
Authority: WO
Inventors: 林建民
Original assignee: 广州视源电子科技股份有限公司
Priority date: 2016-07-13
Filing date: 2016-12-29
Publication date: 2018-01-18
Also published as: CN106228546A; CN106228546B

Abstract

A board inspection method, comprising: acquiring an image to be inspected of an inspection region located on a conveyor belt (S101); matching the image to be inspected with a pre-configured template image to obtain a similarity level between the image to be inspected and the template image (S102); if the similarity level is less than a preset threshold, performing binarization on the image to be inspected to obtain a binary image (S103); extracting all contours of the binary image and computing an area of connecting regions enclosed by the contours, so as to obtain an area of a minimum bounding rectangle having a maximum area of the connecting regions (S104); and when a ratio between the area of the minimum bounding rectangle and an area of the binary image is greater than or equal to a preset ratio, determining the board has entered the inspection region (S105). A board inspection device is further provided. The inspection method and device can accurately determine whether a board has entered the inspection region or not.

Description

Method and device for detecting board

Technical field

The invention relates to the field of automatic optical detection, in particular to a method and a device for detecting a card.

Background technique

Automated optical inspection is an essential part of the industrial production process. The principle is to obtain the surface state of the finished product through optical imaging, and to detect foreign matter or surface defects on the finished product by image processing. Among them, determining whether the finished product enters the detection area is a key step of automatic optical detection.

In the detection of the solder surface of the PCB board, it is necessary to use three-color illumination of different angles to highlight the three-dimensional information of the solder. At the same time, in order to avoid the influence of parallax, the telecentric lens is usually used in the detection. To take an image of the solder surface. The above two factors will limit the size of the field of view of the camera. At present, the image acquisition field of the solder surface inspection is generally 250*320mm~510*460mm, which is smaller than the area of the board itself, that is, it needs to pass the partial shooting board. Method to shoot.

In the prior art, when entering the solder surface of the board, the time and coordinates of the board entering the field of view of the camera are mainly provided by the mechanical structure. However, this method relies greatly on the accuracy of the mechanical motion structure, and the high-precision mechanical motion structure often means high cost and more mechanical maintenance work, which is not conducive to reducing the detection cost.

Summary of the invention

In view of the above problems, an object of the present invention is to provide a method and apparatus for detecting a card, which can accurately detect whether a card enters a detection area without requiring a high-precision structure.

The invention provides a method for detecting a board, comprising the following steps:

Acquiring an image to be tested of the detection area located on the conveyor belt;

Matching the image to be tested with a preset template image to obtain a similarity between the image to be tested and the template image; wherein the template image is an area of the card in the detection area and the An image when the ratio of the area of the detection area is a predetermined ratio;

When the similarity is less than a preset threshold, the image to be tested is binarized to obtain a binary image of the image to be tested;

Extracting all contours on the binary image, calculating an area of the connected region surrounded by the contour, and obtaining an area of a minimum circumscribed rectangle of the connected region having the largest area;

When the ratio of the area of the minimum circumscribed rectangle to the area of the binary image is greater than or equal to the predetermined ratio value, it is determined that the board enters the detection area.

Preferably, before the image to be tested is matched with the preset template image to obtain the similarity between the image to be tested and the template image, the method further includes:

The boundary of the image to be tested is expanded, wherein the expanded portion is filled with pixels having a gray value of 0.

Preferably, when the similarity is less than a preset threshold, the image to be tested is binarized to obtain a binary image of the image to be tested, and specifically includes:

When the similarity is less than a preset threshold, calculating an HSV value of each pixel of the image to be tested according to an RGB value of each pixel of the image to be tested, where H is a hue, and S is Saturation, V is a value;

Comparing the HSV value of each pixel of the image to be tested with the HSV value of the preset color of the board bottom layer, and determining whether the pixel point matches the color of the board bottom board; if yes, Setting the gray value of the pixel to be 1 on the image to be tested, and if not, setting the gray value of the pixel to 0 on the image to be tested; wherein, when the image to be tested The difference between the H value of one pixel and the H value of the color of the board bottom is less than a preset error, and the difference between the S value of the pixel of the image to be tested and the S value of the color of the board bottom is less than a preset error, the difference between the V value of the pixel of the image to be tested and the V value of the color of the board substrate is less than a preset error, and the pixel of the image to be tested is simultaneously established. Matching the color of the board base plate;

After the HSV value of all the pixels of the image to be tested is compared with the HSV value of the preset board bottom color, a binary image is generated.

Preferably, before extracting all the contours on the binary image, calculating the area of the connected area surrounded by the outline, and obtaining the area of the minimum circumscribed rectangle of the connected area having the largest area, the method further includes:

A morphological closing operation is performed on the binary image to perform morphological filling and noise cancellation on the binary image.

Preferably, when the absolute value of the difference between the similarity and 1 is less than a preset allowable value, it is determined that the image to be tested is an image that the card enters the detection area for the first time.

Preferably, the predetermined ratio is 1/4.

The invention also provides a detecting device for a card, comprising:

An acquisition unit, configured to collect an image to be tested of a detection area located on the conveyor belt;

a similarity matching unit, configured to match the image to be tested with a preset template image to obtain a similarity between the image to be tested and the template image; wherein the template image is a card in the detecting An image when the ratio of the area within the area to the area of the detection area is a predetermined ratio;

a binarization unit, configured to perform binarization on the image to be tested when the similarity is less than a preset threshold, to obtain a binary image of the image to be tested;

a contour extracting unit, configured to extract all contours on the binary image, calculate an area of the connected region surrounded by the contour, and obtain an area of a minimum circumscribed rectangle of the connected region having the largest area;

And a ratio calculating unit configured to determine that the card enters the detection area when a ratio of an area of the minimum circumscribed rectangle to an area of the binary image is greater than or equal to the predetermined ratio value.

Preferably, the method further comprises:

And an expansion unit, configured to expand a boundary of the image to be tested, wherein the extended portion is filled with pixels with a gray value of 0.

Preferably, the binarization unit specifically includes:

And an HSV value calculation module, configured to: when the similarity is less than a preset threshold, calculate an HSV value of each pixel of the image to be tested according to an RGB value of each pixel of the image to be tested, where , H is the hue, S is the saturation, and V is the value;

a matching module, configured to compare an HSV value of each pixel of the image to be tested with a preset HSV value of a board bottom color, and determine whether the pixel point matches a color of the board bottom layer; If yes, the gray value of the pixel is set to 1 on the image to be tested, and if not, the gray value of the pixel is set to 0 on the image to be tested; The difference between the H value of one pixel of the image to be tested and the H value of the color of the board substrate is less than a preset error, and the S value of the pixel of the image to be tested and the color of the board bottom layer The difference of the S value is smaller than the preset error, and the difference between the V value of the pixel of the image to be tested and the V value of the color of the board bottom layer is less than the preset error. The pixel of the image matches the color of the board backplane;

The binary image generating module is configured to generate a binary image after the HSV value of all the pixels of the image to be tested is compared with the HSV value of the preset color of the board bottom color.

Preferably, the method further comprises:

The morphological closing unit is configured to perform a morphological closing operation on the binary image to perform morphological filling and noise elimination on the binary image.

The method and device for detecting a card provided by the embodiment of the present invention, after binarizing the image to be tested, according to the area of the minimum circumscribed rectangle of the connected area having the largest area on the binary image and the second The ratio of the area of the value image determines whether the card enters the detection area, so that it is possible to accurately determine whether the card enters the detection area without requiring a high-precision mechanical movement structure.

DRAWINGS

In order to more clearly illustrate the technical solutions of the present invention, the drawings used in the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present invention, which are common in the art. For the skilled person, other drawings can be obtained from these drawings without any creative work.

FIG. 1 is a schematic flow chart of a method for detecting a card provided by an embodiment of the present invention.

FIG. 2 is a schematic diagram of an image to be tested according to an embodiment of the present invention.

3(a) to 3(a) are schematic diagrams of template images provided by an embodiment of the present invention.

4 is a schematic diagram of a binary image provided by an embodiment of the present invention.

Figure 5 is a schematic illustration of the minimum circumscribed rectangle defining the connected region having the largest area on the binary image.

FIG. 6 is a schematic diagram of expanding the image to be tested of FIG. 2. FIG.

Fig. 7 is a schematic diagram showing the morphological closing operation of the binary image of Fig. 4;

FIG. 8 is a schematic structural diagram of a device for detecting a card provided by an embodiment of the present invention.

9 is a schematic structural view of the binarization unit of FIG. 8.

FIG. 10 is a schematic structural diagram of a detecting device for a card provided by a preferred embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

The embodiment of the invention provides a method and a device for detecting a card, which are used for detecting a card (such as a PCB card), in particular, whether the solder surface of the card enters a detection area on the conveyor. The following is a detailed description.

Referring to FIG. 1 , an embodiment of the present invention provides a method for detecting a card. The method for detecting the card may be implemented by a detecting device of the card, and at least includes the following steps:

S101. Acquire an image to be tested of a detection area located on a conveyor belt.

As shown in FIG. 2, in the embodiment of the present invention, the conveyor belt can continuously transport the card in a certain conveying direction, and the detecting device of the card collects an image of the card in the transportation, specifically, the The detection device of the card may include a camera that is mounted above the conveyor belt and acquires an image of the detection area on the conveyor belt in real time. The detection area is the image acquisition field of view of the camera.

In the embodiment of the present invention, in order to detect the surface property of the solder surface of the card, in order to highlight the three-dimensional information of the solder surface, it is necessary to illuminate the detection area with three-color light of different angles, and further, in order to avoid In the detection, the camera also uses a telecentric lens for shooting. These two factors will limit the camera to take pictures The field of view size, the image acquisition field of the camera currently detected on the solder surface is generally 250*320mm~510*460mm, and its length and/or width may be smaller than the size of the board itself, that is, it is often required to pass local Shoot the board and shoot it.

S102: Match the image to be tested with a preset template image to obtain a similarity between the image to be tested and the template image, where the template image is an area of the card in the detection area. An image when the ratio of the area of the detection area is a predetermined ratio.

In the embodiment of the present invention, the template image is an image when a ratio of an area of the card in the detection area to a total area of the detection area is a predetermined ratio, wherein the predetermined ratio is a predefined value. A threshold value for the board to enter the detection area is determined. For example, when the detecting device of the card sets that the ratio of the area of the card to the area of the detection area is greater than or equal to one quarter, the card enters the detection area, and the The template image is an image acquired when the ratio of the area of the board to the area of the detection area is exactly one quarter.

Of course, it should be understood that, in the embodiment of the present invention, one quarter is only a reference parameter, which may also be set to 1/6, 1/8, 1/2 or other values according to actual needs, and the present invention No specific restrictions.

Furthermore, as shown in FIGS. 3(a) to 3(c), it should also be understood that the template image is also related to the direction of movement and initial placement of the card on the conveyor belt, and the card is The portion within the detection area should be the portion where it first enters the detection area.

In the embodiment of the present invention, the similarity between the image to be tested and the template image may be obtained by:

Let T(x, y) be the template image, I(x, y) be the image to be tested, first calculate the image of the template image and the image to be measured minus the mean value by the following formula:

T '(x', y ' ) = T (x', y ') - 1 / (w · h) · Σ x ", y" T (x ", y")

I'(x+x',y+y')=I(x+x',y+y')-1/(w·h)·Σ _{x′′,y′′} I(x+x′′,y+ y").

Where x and y are the coordinates of the points on the corresponding image, and w and h are the width and height of the image, respectively.

Then calculate the similarity by the following formula:

Of course, it should be understood that the similarity between the image to be tested and the template image can be calculated by other algorithms, which is not specifically limited by the present invention.

S103. When the similarity is less than a preset threshold, binarize the image to be tested to obtain a binary image of the image to be tested.

In the embodiment of the present invention, if the similarity is equal to 1, the area of the board in the detection area at the time is described. The ratio of the area of the detection area is exactly the preset ratio, that is, when the similarity is 1, it is the time point when the board enters the detection area for the first time. Of course, since it is difficult to ensure that the similarity is 1 can be obtained, from a less strict point of view, when the absolute value of the difference between the similarity and 1 is less than a preset allowable value (for example, 0.01), it can be considered as It is the time point when the board enters the detection area for the first time.

However, even if the similarity is less than or equal to the preset threshold, the board cannot be considered to have not entered the detection area, for example, slight changes in illumination or errors in mechanical structure may affect similarity. Calculation results. Therefore, when the similarity is less than a preset threshold, the detecting device of the card further calculates a binary image of the image to be tested for further judgment.

Specifically, step S103 may include:

S1031, when the similarity is less than a preset threshold, calculating an HSV value of each pixel of the image to be tested according to an RGB value of each pixel of the image to be tested, where H is a hue, S is the saturation and V is the value.

Wherein, the HSV value of the image to be tested can be calculated by the following method:

Converting the RGB value of each pixel on the image to be tested into an HSV value, and the conversion formula is as follows:

V=C _max

Thus, the HSV value of each pixel on the image to be tested is obtained, where H is the hue, S is the saturation, and V is the value.

S1032. Align the HSV value of each pixel of the image to be tested with the HSV value of the preset color of the board bottom layer, and determine whether the pixel point matches the color of the board bottom board.

In the embodiment of the present invention, when the standard layout of the board is made, the color of the bottom surface of the soldering surface of the board can be obtained. For example, for the green board, the color of the bottom board is green, and the board can be obtained by the above conversion formula. Base plate color HSV The value of the card detecting device can store the HSV value of the color of the board bottom plate. Then, the detecting device of the card compares the HSV value of each pixel of the image to be tested with the HSV value of the color of the board bottom plate, and determines whether the pixel point and the color of the board bottom layer Matching; if yes, setting the gray value of the pixel to 1 on the image to be tested, and if not, setting the gray value of the pixel to 0 on the image to be tested. It should be noted that the gray value here is a normalized gray value, that is, the gray value is 0 for all black, and the gray value is 1 for all white.

The matching process is: when the difference between the H value of one pixel of the image to be tested and the H value of the color of the board bottom is less than a preset error, the S value of the pixel of the image to be tested The difference between the S value and the color of the board bottom plate is less than a preset error, and the difference between the V value of the pixel of the image to be tested and the V value of the color of the board bottom plate is less than a preset error. At the same time, the pixel of the image to be tested matches the color of the board bottom plate. If at least one of the three conditions is not satisfied, the pixel of the image to be tested does not match the color of the board bottom board. . The specific calculation process is as follows:

Where H _background , S _background , V _background represent the HSV value of the color of the board base plate, H _test (i, j), S _test (i, j), V _test (i, j) is the image to be tested (i , j) the HSV value at the coordinates, and C is the allowable error.

S1033: After comparing the HSV value of all the pixel points of the image to be tested with the HSV value of the preset board bottom color, a binary image is generated.

The generated binary image can be as shown in FIG. 4 .

S104, extracting all contours on the binary image, calculating an area of the connected area surrounded by the outline, and obtaining an area of a minimum circumscribed rectangle of the connected area having the largest area.

Specifically, after generating the binary image, an outline on the binary image may be acquired, wherein the extraction of the contour may be implemented according to an existing algorithm, for example, when determining a pixel point with a gray value of 1 The gray values of adjacent pixels are all 1, and the point is the inner point of the contour, and vice versa. Contour extraction is done by setting all interior points to background points.

As shown in FIG. 5, after the outline is extracted, the detecting means of the card calculates the area of the connected area surrounded by the outline, and calculates the area of the minimum circumscribed rectangle of the connected area having the largest area.

S105. When the ratio of the area of the minimum circumscribed rectangle to the area of the binary image is greater than or equal to the predetermined ratio value, determine that the card enters the detection area.

In the embodiment of the present invention, after the area of the minimum circumscribed rectangle is obtained, the detecting device of the card determines whether the ratio of the area of the circumscribed rectangle to the area of the binary image is greater than the predetermined ratio If yes, then the description The board has entered the detection area, otherwise it indicates that the board has not entered the detection area.

In summary, the method for detecting a board provided by the embodiment of the present invention, after binarizing the image to be tested, according to the area of the minimum circumscribed rectangle of the connected area having the largest area on the binary image The ratio of the area of the binary image determines whether the card enters the detection area, so that it is possible to accurately determine whether the card enters the detection without requiring a high-precision mechanical motion structure. within the area.

In order to facilitate an understanding of the present invention, some preferred embodiments of the present invention are further described below.

First preferred embodiment:

Since the mechanical structure itself has an offset error, the card may be deviated from the actual expectation when the card is moved on the conveyor belt, so that the detected image captured by the camera and the card position obtained by the template image are captured. There is a position offset. In order to eliminate the error caused by the positional shift, the preferred implementation before step S102 further includes:

Specifically, as shown in FIG. 6, FIG. 6 is a result of expanding FIG. 2, by which the error due to the positional deviation of the mechanical structure is eliminated, so that the calculation result of the similarity is more accurate. .

A second preferred embodiment:

As shown in Figure 5, when binarizing, there will be a lot of noise, which will affect the contour extraction. Therefore, before extracting the contour, you need to eliminate these noises.

To this end, in the preferred embodiment, before step S104, the method further includes:

As shown in Fig. 7, Fig. 7 shows the binary image after the morphological closing operation, and it can be seen that most of the noise has been eliminated, thereby ensuring accurate extraction of the contour.

Referring to FIG. 8, an embodiment of the present invention further provides a card detecting apparatus 100, including:

The collecting unit 10 is configured to collect an image to be tested of the detection area located on the conveyor belt.

a similarity matching unit 20, configured to match the image to be tested with a preset template image to obtain a similarity between the image to be tested and the template image; wherein the template image is a card in the An image when the ratio of the area in the detection area to the area of the detection area is a predetermined ratio.

The binarization unit 30 is configured to perform binarization on the image to be tested when the similarity is less than a preset threshold to obtain a binary image of the image to be tested.

Specifically, please refer to FIG. 9 together, the binarization unit 30 specifically includes an HSV value calculation module 31 and a matching module. 32 and binary image generation module 33, wherein:

The HSV value calculation module 31 is configured to: when the similarity is less than a preset threshold, calculate an HSV of each pixel of the image to be tested according to an RGB value of each pixel of the image to be tested. Value, where H is the hue, S is the saturation, and V is the value.

The matching module 32 is configured to compare an HSV value of each pixel of the image to be tested with a HSV value of a preset color of the board bottom layer, and determine whether the pixel point and the board bottom color Matching; if yes, setting the gray value of the pixel to 1 on the image to be tested, and if not, setting the gray value of the pixel to 0 on the image to be tested.

Wherein, when the difference between the H value of one pixel of the image to be tested and the H value of the color of the board substrate is less than a preset error, the S value of the pixel of the image to be tested and the board The difference between the S values of the color of the bottom plate is smaller than a preset error, and the difference between the V value of the pixel of the image to be tested and the V value of the color of the bottom plate of the board is less than the preset error, and the three conditions are simultaneously established. The pixel of the image to be tested matches the color of the board backplane.

The binary image generating module 33 is configured to generate a binary image after completing an alignment of the HSV value of all the pixel points of the image to be tested with the HSV value of the preset board bottom color.

The contour extracting unit 40 is configured to extract all the contours on the binary image, calculate the area of the connected region surrounded by the contour, and obtain the area of the minimum circumscribed rectangle of the connected region having the largest area.

The ratio calculating unit 50 is configured to determine that the card enters the detection area when a ratio of an area of the minimum circumscribed rectangle to an area of the binary image is greater than or equal to the predetermined ratio.

In summary, the detecting device 100 for the card provided by the embodiment of the present invention binarizes the image to be tested by the binarization unit 30, and then calculates the maximum value on the binary image according to the contour extracting unit 40. Determining, by the ratio calculating unit 50, a ratio of an area of the minimum circumscribed rectangle to an area of the binary image to determine whether the card enters the detection area, thereby determining an area of the minimum circumscribed rectangle of the connected area of the area In the case where a high-precision mechanical motion structure is not required, it is also possible to accurately judge whether or not the board enters the detection area.

Referring to FIG. 9 together, preferably, the detecting device 100 of the card further comprises:

The expansion unit 60 is configured to expand a boundary of the image to be tested, wherein the extended portion is filled with pixels with a gray value of 0.

Preferably, the detecting device 100 of the card further comprises:

The morphological closing unit 70 is configured to perform a morphological closing operation on the binary image to perform morphological filling and noise elimination on the binary image.

The above disclosure is only a preferred embodiment of the present invention, and of course, the scope of the present invention is not limited thereto, and those skilled in the art can understand all or part of the process of implementing the above embodiments, and according to the present invention. The equivalent changes required are still within the scope of the invention.

One of ordinary skill in the art can understand that all or part of the process of implementing the foregoing embodiments can be completed by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium. When executed, the flow of an embodiment of the methods as described above may be included. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

Claims

A method for detecting a card, comprising the steps of:

Acquiring an image to be tested of the detection area located on the conveyor belt;

Matching the image to be tested with a preset template image to obtain a similarity between the image to be tested and the template image; wherein the template image is an area of the card in the detection area and the An image when the ratio of the area of the detection area is a predetermined ratio;

When the similarity is less than a preset threshold, the image to be tested is binarized to obtain a binary image of the image to be tested;

Extracting all contours on the binary image, calculating an area of the connected region surrounded by the contour, and obtaining an area of a minimum circumscribed rectangle of the connected region having the largest area;

When the ratio of the area of the minimum circumscribed rectangle to the area of the binary image is greater than or equal to the predetermined ratio value, it is determined that the board enters the detection area.
The method for detecting a card according to claim 1, wherein before the image to be tested is matched with a preset template image to obtain a similarity between the image to be tested and the template image, include:

The boundary of the image to be tested is expanded, wherein the expanded portion is filled with pixels having a gray value of 0.
The method for detecting a card according to claim 1, wherein when the similarity is less than a preset threshold, the image to be tested is binarized to obtain the image to be tested. Value image, including:

When the similarity is less than a preset threshold, calculating an HSV value of each pixel of the image to be tested according to an RGB value of each pixel of the image to be tested, where H is a hue, and S is Saturation, V is a value;

Comparing the HSV value of each pixel of the image to be tested with the HSV value of the preset color of the board bottom layer, and determining whether the pixel point matches the color of the board bottom board; if yes, Setting the gray value of the pixel to be 1 on the image to be tested, and if not, setting the gray value of the pixel to 0 on the image to be tested; wherein, when the image to be tested The difference between the H value of one pixel and the H value of the color of the board bottom is less than a preset error, and the difference between the S value of the pixel of the image to be tested and the S value of the color of the board bottom is less than a preset error, the difference between the V value of the pixel of the image to be tested and the V value of the color of the board substrate is less than a preset error, and the pixel of the image to be tested is simultaneously established. Matching the color of the board base plate;

After the HSV value of all the pixels of the image to be tested is compared with the HSV value of the preset board bottom color, a binary image is generated.
The method for detecting a board according to claim 1, wherein all contours on said binary image are extracted, an area of a connected area surrounded by said outline is calculated, and a connected area having a largest area is obtained Before the area of the smallest circumscribed rectangle, it also includes:

A morphological closing operation is performed on the binary image to perform morphological filling and noise cancellation on the binary image.
The method for detecting a card according to claim 1, wherein when the absolute value of the difference between the similarity and 1 is less than a preset allowable value, determining that the image to be tested is the card number An image that enters the detection area once.
The method of detecting a card according to any one of claims 1 to 5, wherein the predetermined ratio is 1/4.
A device for detecting a card, comprising:

An acquisition unit, configured to collect an image to be tested of a detection area located on the conveyor belt;

a similarity matching unit, configured to match the image to be tested with a preset template image to obtain a similarity between the image to be tested and the template image; wherein the template image is a card in the detecting An image when the ratio of the area within the area to the area of the detection area is a predetermined ratio;

a binarization unit, configured to perform binarization on the image to be tested when the similarity is less than a preset threshold, to obtain a binary image of the image to be tested;

a contour extracting unit, configured to extract all contours on the binary image, calculate an area of the connected region surrounded by the contour, and obtain an area of a minimum circumscribed rectangle of the connected region having the largest area;

And a ratio calculating unit configured to determine that the card enters the detection area when a ratio of an area of the minimum circumscribed rectangle to an area of the binary image is greater than or equal to the predetermined ratio value.
The device for detecting a card according to claim 7, further comprising:

And an expansion unit, configured to expand a boundary of the image to be tested, wherein the extended portion is filled with pixels with a gray value of 0.
The device for detecting a card according to claim 7, wherein the binarization unit specifically comprises:

And an HSV value calculation module, configured to: when the similarity is less than a preset threshold, calculate an HSV value of each pixel of the image to be tested according to an RGB value of each pixel of the image to be tested, where , H is the hue, S is the saturation, and V is the value;

a matching module, configured to compare an HSV value of each pixel of the image to be tested with a preset HSV value of a board bottom color, and determine whether the pixel point matches a color of the board bottom layer; If yes, the gray value of the pixel is set to 1 on the image to be tested, and if not, the gray value of the pixel is set to 0 on the image to be tested; The difference between the H value of one pixel of the image to be tested and the H value of the color of the board substrate is less than a preset error, and the S value of the pixel of the image to be tested and the color of the board bottom layer The difference of the S value is smaller than the preset error, and the difference between the V value of the pixel of the image to be tested and the V value of the color of the board bottom layer is less than the preset error. The pixel of the image matches the color of the board backplane;

The binary image generating module is configured to generate a binary image after the HSV value of all the pixels of the image to be tested is compared with the HSV value of the preset color of the board bottom color.
The device for detecting a card according to claim 7, further comprising:

The morphological closing unit is configured to perform a morphological closing operation on the binary image to perform morphological filling and noise elimination on the binary image.