Method, device and equipment for detecting defects of vehicle-mounted display screen under film covering condition and medium

Abstract

The invention discloses a vehicle-mounted display screen defect detection method, device, equipment and medium under a film covering condition, and the method comprises the steps: controlling a CCD camera to image a display screen to be detected, and obtaining an image A; controlling the CCD camera to image the display screen to be detected to obtain an image C; performing first feature extraction and potential defect point positioning; turning off the four strip-shaped light sources, and controlling the CCD camera to image the display screen to be detected to obtain an image H; performing secondary feature extraction and potential defect point positioning; turning off the four strip-shaped light sources, and controlling the CCD camera to image the display screen to be detected to obtain an image O; third-time feature extraction and potential defect point positioning are carried out; all real defects are screened out; according to the invention, by adding the lateral auxiliary light source and a related algorithm, the defect detection of the vehicle-mounted display screen under the condition of no film tearing can be realized, the universality is realized, the manual film tearing is canceled, the labor intensity is reduced, the risk of screen scratch is reduced, and the yield of the product after detection is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle-mounted display screens, and in particular to a method, device, equipment and medium for detecting defects of vehicle-mounted display screens under lamination conditions. Background Art

[0002] The in-vehicle display screen is the main carrier of human-vehicle interaction, and its display quality is directly related to the user experience. Therefore, in the production and manufacturing process of in-vehicle display screens, it is necessary to use machine vision methods to detect display defects to prevent defective products from flowing out, thereby ensuring product quality. However, since the protective film on the surface of the display screen may contain foreign matter such as bubbles and particles, in order to eliminate the influence of foreign matter on the protective film on the test results during the detection process, the traditional detection method requires the protective film on the surface of the screen to be torn off before the test. However, this method requires the addition of manual film tearing action, and there is a risk of scratching the screen surface. Therefore, in order to reduce the risks brought by the film tearing operation, it is necessary to develop a method, device, equipment and medium for defect detection of in-vehicle display screens that does not require film tearing. Summary of the invention

[0003] The main purpose of the present invention is to provide a method, device, equipment and medium for detecting defects of a vehicle display screen under lamination conditions, aiming to solve the existing technical problems.

[0004] To achieve the above object, the present invention provides a method for detecting defects of a vehicle display screen under lamination conditions, comprising:

[0005] The host computer controls the black screen state of the display screen to be detected, and controls the CCD camera to image the display screen to be detected, and obtains image A;

[0006] Perform black background adaptive modeling on image A;

[0007] The host computer controls the display screen to be inspected to be in black screen state, turns on four high-uniformity strip lights, and controls the CCD camera to image the display screen to be inspected to obtain image C;

[0008] Carry out the first feature extraction and potential defect point location;

[0009] Turn off the four bar light sources, control the display screen to display a white image with a brightness of 50%, and control the CCD camera to image the display screen to be inspected to obtain image H;

[0010] Perform the second feature extraction and potential defect point location;

[0011] Turn off the four bar light sources, control the display screen to display a white image with a brightness of 100%, and control the CCD camera to image the display screen to be inspected to obtain image O;

[0012] Perform the third feature extraction and potential defect point location;

[0013] Screen out all real defects.

[0014] Furthermore, the black background adaptive modeling of image A includes, for image A, background modeling is performed by the following formula to calculate the noise characteristics of the display screen in a black screen state: B=AI; wherein B represents a noise image, and I represents an image whose size is consistent with A and whose pixel values ​​are all 1.

[0015] Furthermore, the first feature extraction and potential defect point location includes calculating the image D after removing the background noise by the following formula:

[0016] D=CB

[0017] Perform opening operations on image D to obtain the result image E; then calculate the enhanced image G using the following formula:

[0018] G=D-E+mean(E)

[0019] Where, mean(E) is the mean of image E;

[0020] The image G is binarized with a fixed threshold to obtain a binary image F, and then the connected domain detection method is used to obtain the potential defect set {V1}.

[0021] Furthermore, the second feature extraction and potential defect point location includes calculating the image J after removing the background noise by the following formula:

[0022] J=HB

[0023] Perform opening and closing operations on image J to obtain result images K and L; then calculate the enhanced image M using the following formula:

[0024] M=JKL

[0025] The image M is binarized with a fixed threshold to obtain a binary image N, and then the connected domain detection method is used to obtain the potential defect set {V2}.

[0026] Furthermore, the third feature extraction and potential defect point location includes calculating the image P after removing the background noise by the following formula:

[0027] P=OB

[0028] Perform opening and closing operations on the image P to obtain the result images Q and R; then calculate the enhanced image S using the following formula:

[0029] S=PQ-R+mean(Q)+mean(R)

[0030] Where mean(Q) and mean(R) are the means of images Q and R respectively.

[0031] The image S is binarized with a fixed threshold to obtain a binary image T, and then the connected domain detection method is used to obtain the potential defect set {V3}.

[0032] Furthermore, the screening out of all real defects includes, for each potential defect in the set {V3}, calculating its centroid coordinates (x3, y3), and calculating its distance from the centroid coordinates (x1, y1) and (x2, y2) of each defect in the sets {V1} and {V2} by the following formula:

[0033]

[0034] Set the threshold UT 31 and UT 32 , all candidate defects in the set {V3} that meet the following conditions are judged as real defects:

[0035] U 31 >UT 31

[0036] U 32 >UT 32

[0037] Repeat the above steps to filter out all real defects.

[0038] A vehicle display screen defect detection device under lamination conditions, comprising:

[0039] A CCD camera, with a low-distortion lens and a circular polarizer installed at the lens end in sequence, for imaging the vehicle display screen;

[0040] A light source device is arranged around the vehicle-mounted display screen and is used to provide a light source with adjustable brightness;

[0041] The host computer is used to control the CCD camera imaging and adjust the light source of the light source equipment.

[0042] A device comprises: a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the above-mentioned method for detecting defects of a vehicle display screen under lamination conditions.

[0043] A storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the above-mentioned method for detecting defects of a vehicle display screen under lamination conditions are implemented.

[0044] The beneficial effects of the present invention are embodied in:

[0045] In the present invention, by adding lateral auxiliary light sources and related algorithms, vehicle display screen defect detection can be achieved without film tearing, which is universal, eliminates manual film tearing, reduces labor intensity, reduces the risk of screen scratches, and improves the product yield after detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the process of the vehicle display screen defect detection method under the lamination condition of the present invention;

[0047] Figure 2 It is a schematic diagram of the structure of the vehicle display screen defect detection device under the lamination condition of the present invention.

[0048] Description of reference numerals:

[0049] 100. CCD camera; 200. light source equipment; 300. host computer; 400. light source controller. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. In the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0051] See also Figure 1 The present invention provides a method for detecting defects of a vehicle display screen under a lamination condition, comprising:

[0052] The host computer controls the black screen state of the display screen to be detected, and controls the CCD camera to image the display screen to be detected, and obtains image A;

[0053] Perform black background adaptive modeling on image A;

[0054] The host computer controls the display screen to be inspected to be in black screen state, turns on four high-uniformity strip lights, and controls the CCD camera to image the display screen to be inspected to obtain image C;

[0055] Carry out the first feature extraction and potential defect point location;

[0056] Turn off the four bar light sources, control the display screen to display a white image with a brightness of 50%, and control the CCD camera to image the display screen to be inspected to obtain image H;

[0057] Perform the second feature extraction and potential defect point location;

[0058] Turn off the four bar light sources, control the display screen to display a white image with a brightness of 100%, and control the CCD camera to image the display screen to be inspected to obtain image O;

[0059] Perform the third feature extraction and potential defect point location;

[0060] Screen out all real defects.

[0061] The black background adaptive modeling of image A includes, for image A, background modeling is performed by the following formula to calculate the noise characteristics of the display screen in a black screen state: B=AI; wherein B represents a noise image, and I represents an image with a size consistent with A and a pixel value of 1.

[0062] The first feature extraction and potential defect point location includes calculating the image D after removing the background noise by the following formula:

[0063] D=CB

[0064] Perform opening operations on image D to obtain the result image E; then calculate the enhanced image G using the following formula:

[0065] G=D-E+mean(E)

[0066] Where, mean(E) is the mean of image E;

[0067] The image G is binarized with a fixed threshold to obtain a binary image F, and then the connected domain detection method is used to obtain the potential defect set {V1}.

[0068] The second feature extraction and potential defect point location includes calculating the image J after removing the background noise by the following formula:

[0069] J=HB

[0070] Perform opening and closing operations on image J to obtain result images K and L; then calculate the enhanced image M using the following formula:

[0071] M=JKL

[0072] The image M is binarized with a fixed threshold to obtain a binary image N, and then the connected domain detection method is used to obtain the potential defect set {V2}.

[0073] The third feature extraction and potential defect point location includes calculating the image P after removing the background noise by the following formula:

[0074] P=OB

[0075] Perform opening and closing operations on the image P to obtain the result images Q and R; then calculate the enhanced image S using the following formula:

[0076] S=PQ-R+mean(Q)+mean(R)

[0077] Where mean(Q) and mean(R) are the means of images Q and R respectively.

[0078] The image S is binarized with a fixed threshold to obtain a binary image T, and then the connected domain detection method is used to obtain the potential defect set {V3}.

[0079] The screening of all real defects includes, for each potential defect in the set {V3}, calculating its centroid coordinates (x3, y3), and calculating its distance from the centroid coordinates (x1, y1) and (x2, y2) of each defect in the sets {V1} and {V2} by the following formula:

[0080]

[0081] Set the threshold UT 31 and UT 32 , all candidate defects in the set {V3} that meet the following conditions are judged as real defects:

[0082] U 31 >UT 31

[0083] U 32 >UT 32

[0084] Repeat the above steps to filter out all real defects.

[0085] A vehicle display screen defect detection device under lamination conditions, comprising:

[0086] A CCD camera 100, whose lens end is sequentially mounted with a low-distortion lens and a circular polarizer, is used to image the vehicle-mounted display screen;

[0087] The light source device 200 is arranged around the vehicle-mounted display screen and is used to provide a light source with adjustable brightness;

[0088] The host computer 300 is used to control the imaging of the CCD camera 100 and adjust the light source of the light source device 200 .

[0089] A light source controller 400 is also included for adjusting the brightness of the light source device 200 .

[0090] A device comprises: a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the above-mentioned method for detecting defects of a vehicle display screen under lamination conditions.

[0091] A storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the above-mentioned method for detecting defects of a vehicle display screen under lamination conditions are implemented.

[0092] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0093] In addition, for technical details not fully described in this embodiment, reference can be made to the vehicle display screen defect detection method under lamination conditions provided in any embodiment of the present invention, and will not be repeated here.

[0094] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0095] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0096] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0097] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for detecting defects in vehicle display screens under lamination conditions, characterized in that ,include: The host computer controls the black screen state of the display screen to be detected, and controls the CCD camera to image the display screen to be detected, and obtains image A; Perform black background adaptive modeling on image A; The host computer controls the display screen to be inspected to be in black screen state, turns on four high-uniformity strip lights, and controls the CCD camera to image the display screen to be inspected to obtain image C; Carry out the first feature extraction and potential defect point location; Turn off the four bar light sources, control the display screen to display a white image with a brightness of 50%, and control the CCD camera to image the display screen to be inspected to obtain image H; Perform the second feature extraction and potential defect point location; Turn off the four bar light sources, control the display screen to display a white image with a brightness of 100%, and control the CCD camera to image the display screen to be inspected to obtain image O; Perform the third feature extraction and potential defect point location; Screen out all real defects.

2. The method for detecting defects of a vehicle display screen under lamination conditions according to claim 1, characterized in that: The adaptive black background modeling of the image A includes, for the image A, performing background modeling by the following formula to calculate the noise characteristics of the display screen in a black screen state: B = AI; In the formula, B represents the noise image, and I represents an image with the same size as A and pixel values ​​of 1.

3. The method for detecting defects of a vehicle display screen under lamination conditions according to claim 1, characterized in that: The first feature extraction and potential defect point location includes calculating the image D after removing the background noise by the following formula: D=CB Perform opening operations on image D to obtain the result image E; then calculate the enhanced image G using the following formula: G=D-E+mean(E) Where, mean(E) is the mean of image E; The image G is binarized with a fixed threshold to obtain a binary image F, and then the connected domain detection method is used to obtain the potential defect set {V1}.

4. The method for detecting defects of a vehicle display screen under lamination conditions according to claim 1, characterized in that: The second feature extraction and potential defect point location includes calculating the image J after removing the background noise by the following formula: J=HB Perform opening and closing operations on image J to obtain result images K and L; then calculate the enhanced image M using the following formula: M=JKL The image M is binarized with a fixed threshold to obtain a binary image N, and then the connected domain detection method is used to obtain the potential defect set {V2}.

5. The method for detecting defects of a vehicle display screen under lamination conditions according to claim 1, characterized in that: The third feature extraction and potential defect point location includes calculating the image P after removing the background noise by the following formula: P=OB Perform opening and closing operations on the image P to obtain the result images Q and R; then calculate the enhanced image S using the following formula: S=PQ-R+mean(Q)+mean(R) Where mean(Q) and mean(R) are the means of images Q and R respectively. The image S is binarized with a fixed threshold to obtain a binary image T, and then the connected domain detection method is used to obtain the potential defect set {V3}.

6. The method for detecting defects of a vehicle display screen under lamination conditions according to claim 1, characterized in that: The screening of all real defects includes, for each potential defect in the set {V3}, calculating its centroid coordinates (x3, y3), and calculating its distance from the centroid coordinates (x1, y1) and (x2, y2) of each defect in the sets {V1} and {V2} by the following formula: Set the threshold UT 31 and UT 32 , all candidate defects in the set {V3} that meet the following conditions are judged as real defects: U 31 >OUT 31 U 32 >OUT 32 Repeat the above steps to filter out all real defects.

7. A vehicle display screen defect detection device under lamination conditions, characterized in that: include, A CCD camera (100), a low-distortion lens and a circular polarizer being sequentially mounted on the lens end thereof, for imaging the vehicle-mounted display screen; A light source device (200) is arranged around the vehicle-mounted display screen and is used to provide a light source with adjustable brightness; The host computer (300) is used to control the imaging of the CCD camera (100) and adjust the light source of the light source device (200).

8. A device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for detecting defects of a vehicle display screen under lamination conditions as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for detecting defects of a vehicle display screen under lamination conditions as described in any one of claims 1 to 6.

Images