A positioning device and method for a liquid crystal display screen detection area

Abstract

This application relates to the technical field of liquid crystal screen detection. Specifically, it relates to a positioning device and method for a detection area of a liquid crystal screen, which can, to a certain extent, solve the problem of inaccurate liquid crystal screen detection results. The multi-panel liquid crystal screen detection area positioning device includes: a collector, a display, and a controller. The controller is configured to: receive a first image including a first frame, and identify the four sides of the first frame; the area in the first frame corresponds to the first area of the product to be tested; determine a first effective side and a second effective side among the four sides according to the position of the first area in the product to be tested; translate the first effective side and the second effective side to obtain corresponding third and fourth corrected sides to form a second frame, and the moving distances of the first effective side and the second effective side are both determined according to the preset size of the first area; the area enclosed by the second frame is the effective area, and the effective area is used to represent the predetermined detection area of the product to be tested.

Description

Technical Field

[0001] The present application relates to the field of liquid crystal screen detection technology, and in particular to a positioning device and method for a liquid crystal screen detection area. Background Art

[0002] With the development of economy, people's consumption demand has been upgraded comprehensively, and the requirements for the picture quality of LCD screens such as TVs and laptops have been continuously improved. LCD screens are developing in the direction of large size and high definition. Before using LCD screens, defects need to be detected to find defective screens in time, so that unqualified products are not easily lost to the market.

[0003] In the process of LCD screen inspection, due to the disadvantage of large errors in traditional manual defect detection, the automatic optical inspection technology (AOI) based on industrial image collectors gradually replaced the manual inspection method and became the mainstream of LCD screen defect detection. The LCD screen defect detection system based on machine vision mainly uses a high-definition image collector to collect images of the LCD screen to be inspected in a darkroom environment. During the collection, the LCD screen is illuminated by an LCD screen lighting fixture to switch the LCD screen to different pictures for collection. Finally, the defect detection system performs defect detection on the different pictures collected. For small-sized LCD screens, one image collector can be used to detect one product, and the screen defect detection is performed through the above steps; when inspecting large-sized LCD screens, multiple image collectors are usually used for image collection or one image collector is used for mobile image collection. After that, the partial area images collected each time are spliced ​​together for subsequent processing.

[0004] However, in the process of image acquisition by the image acquirer, due to the component errors of the image acquirer and the errors of manual screen placement in actual applications, it is inevitable that the area of ​​the LCD screen photographed by the image acquirer is too large or too small, and it is difficult to capture the predetermined detection area of ​​the screen to be tested every time, which leads to inaccurate subsequent detection results of the LCD screen. Summary of the invention

[0005] In order to solve the problem of inaccurate detection results of LCD screens, the present application provides a positioning device and method for a LCD screen detection area.

[0006] The embodiment of the present application is implemented as follows:

[0007] A first aspect of an embodiment of the present application provides a positioning device for a liquid crystal screen detection area, including:

[0008] A collector, which is set to be at least one, and the collector is used to collect images of the object to be tested;

[0009] A display, for displaying a user interface;

[0010] A controller, configured to:

[0011] Receive a first image including a first frame, and identify four sides of the first frame; an area in the first frame corresponds to a first area of the article to be tested;

[0012] Determine a first effective side and a second effective side among the four sides according to the position of the first area in the article to be tested;

[0013] Translate the first effective side and the second effective side to obtain corresponding third corrected sides and fourth corrected sides, so as to form a second frame, and the moving distances of the first effective side and the second effective side are both determined according to a preset size of the first area;

[0014] Wherein, an area enclosed by the second frame is an effective area, and the effective area is used to represent a predetermined detection area of the article to be tested.

[0015] In some embodiments, the determining the first effective side and the second effective side among the four sides according to the position of the first area in the article to be tested further includes: when the number of the first images is multiple, a sorting method of the multiple first images is preset to be arranged first from left to right and then from top to bottom, and the controller is configured to: determine the position of the first image to be located according to the sorting method, and the position of the first image to be located is the position of the first area in the article to be tested.

[0016] In some embodiments, for the determining the position of the first image to be located according to the sorting method, the controller is further configured to: obtain the number of the first image to be located according to the sorting method of the first image;

[0017] Determine the relationship between the number corresponding to any first image and its row and column according to the sorting method of all the first images, so as to obtain the position of the first image to be located.

[0018] In some embodiments, for the translating the first effective side and the second effective side to obtain corresponding third corrected sides and fourth corrected sides, so as to form a second frame, the controller is further configured to: remove non-effective areas in the first image, so that only the effective area is displayed in the first image.

[0019] In some embodiments, when translating the first effective side and the second effective side to obtain corresponding third corrected side and fourth corrected side to form a second frame, the controller is further configured to: obtain the four vertex coordinates of the second frame, and perform an affine transformation on the vertex coordinates to stretch the effective area into a standard rectangular area. At this time, the effective area is translated to the middle position of the first image.

[0020] The second aspect of the embodiments of the present application provides a method for positioning a detection area of a liquid crystal screen, including the following steps:

[0021] Receive a first image including a first frame, and identify the four sides of the first frame; the area in the first frame corresponds to the first area of the product to be tested;

[0022] According to the position of the first area in the product to be tested, determine the first effective side and the second effective side among the four sides;

[0023] Translate the first effective side and the second effective side to obtain corresponding third corrected side and fourth corrected side to form a second frame, and the moving distances of the first effective side and the second effective side are both determined according to the preset size of the first area;

[0024] Wherein, the area enclosed by the second frame is the effective area, and the effective area is used to represent the predetermined detection area of the product to be tested.

[0025] In some embodiments, in the step of determining the first effective side and the second effective side among the four sides according to the position of the first area in the product to be tested, when the number of the first images is multiple, it is preset that the sorting method of the multiple first images is arranged from left to right first, and then from top to bottom. According to the sorting method, determine the position of the first image to be located, and the position of the first image to be located is the position of the first area in the product to be tested.

[0026] In some embodiments, in the step of determining the position of the first image to be located according to the sorting method, it further includes: obtaining the number of the first image to be located according to the sorting method of the first image;

[0027] According to the sorting method of all the first images, determine the relationship between the number corresponding to any first image and its row and column to obtain the position of the first image to be located.

[0028] In some embodiments, in the step of translating the first effective side and the second effective side to obtain corresponding third corrected side and fourth corrected side to form a second frame, it further includes: removing the non-effective area in the first image so that only the effective area is displayed in the first image.

[0029] In some embodiments, in the step of translating the first effective edge and the second effective edge to obtain corresponding third and fourth corrected edges to form a second frame, the method further includes: obtaining the four vertex coordinates of the second frame, and performing an affine transformation on the vertex coordinates to stretch the effective region into a standard rectangular region. At this time, the effective region is translated to the middle position of the first image.

[0030] Advantages of the present application: By identifying the first effective edge and the second effective edge in the first frame, and moving the first effective edge and the second effective edge according to the preset size of the first region to obtain corresponding third and fourth corrected edges, the first effective edge, the second effective edge, the third corrected edge, and the fourth corrected edge form a second frame. The region enclosed by the second frame is the effective region, which can be used to accurately represent the predetermined detection region of the product to be tested. The size of the effective region is the same as the preset size. At this time, each first image can be an accurate region to be detected, which helps to accurately detect products to be tested such as liquid crystal displays in the subsequent process. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0032] Figure 1 Shows a schematic diagram of the detection result under ideal conditions when detecting the defects of a small-sized screen provided by an embodiment of the present application;

[0033] Figure 2 Shows a three-dimensional structural schematic diagram of a positioning device for a liquid crystal display detection region provided by an embodiment of the present application;

[0034] Figure 3 Shows a schematic diagram of a first image obtained during the operation of a positioning device for a liquid crystal display detection region provided by an embodiment of the present application;

[0035] Figure 4A Shows a schematic diagram of sequentially translating the first effective edge and the second effective edge during the operation of a positioning device for a liquid crystal display detection region provided by an embodiment of the present application;

[0036] Figure 4B Shows a schematic diagram of simultaneously translating the first effective edge and the second effective edge during the operation of a positioning device for a liquid crystal display detection region provided by an embodiment of the present application;

[0037] Figure 5 The figure shows a schematic diagram of the sorting method of the collector during the use of a positioning device for a liquid crystal display (LCD) panel detection area provided by an embodiment of the present application;

[0038] Figure 6 The figure shows a schematic flowchart of a method for positioning a liquid crystal display (LCD) panel detection area provided by an embodiment of the present application;

[0039] Figure 7 The figure shows a schematic diagram of the processing result when a method for positioning a liquid crystal display (LCD) panel detection area provided by the first embodiment of the present application is executed;

[0040] Figure 8 The figure shows a schematic diagram of the processing result when a method for positioning a liquid crystal display (LCD) panel detection area provided by the second embodiment of the present application is executed;

[0041] Figure 9 The figure shows a schematic structural diagram of a system for positioning a liquid crystal display (LCD) panel detection area provided by the first embodiment of the present application;

[0042] Figure 10 The figure shows a schematic structural diagram of a method for positioning a liquid crystal display (LCD) panel detection area provided by the second embodiment of the present application;

[0043] Figure 11 The figure shows a schematic structural diagram of a device for positioning a liquid crystal display (LCD) panel detection area provided by an embodiment of the present application. Detailed implementation manners

[0044] To make the objectives, implementation manners, and advantages of the present application clearer, the following will clearly and completely describe the exemplary implementation manners of the present application with reference to the accompanying drawings in the exemplary embodiments of the present application. Obviously, the described exemplary embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0045] It should be noted that the brief description of the terms in the present application is only for facilitating the understanding of the following described implementation manners, rather than intending to limit the implementation manners of the present application. Unless otherwise specified, these terms should be understood in their ordinary and general meanings.

[0046] The terms "first", "second", "third", etc. in the description, claims, and the above accompanying drawings of the present application are used to distinguish similar or like objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that such terms can be interchanged under appropriate circumstances.

[0047] The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0048] In the process of defect detection of LCD screens waiting to be tested, the minimum detection accuracy is usually required to be 1 sub-pixel. When detecting defects of small-size screens, the ideal situation is that one image collector corresponds to a complete product to be tested. At this time, Figure 1 As shown, the display areas are all within the field of view of the image collector, and the detection area positioning can be achieved using automatic threshold or sliding window method.

[0049] However, the minimum size of conventional large-size panels is 8K, with a resolution of 7680×4320 pixels, which is approximately equal to 23040*12960 sub-pixels. Therefore, to ensure that the optical detection accuracy can meet 1 sub-pixel, the minimum effective target surface of the image collector must be the same as the product sub-pixel size, which is 23040*12960, that is, at least a 300M image collector is used. The most mature and commonly used industrial image collectors with the largest target surface on the market are 151M. Since it is impossible for the image collector to completely cover the effective area of ​​the screen, and in order to be compatible with the later larger size 16K LCD panels, the commonly used optical combination is to use multiple image collectors to collect images at the same time or a multi-piece method of moving one image collector to collect images. When four image collectors collect images at the same time, for example, the image collected by each image collector at a time is a quarter of the area of ​​the product to be tested. Before the visual inspection system performs defect analysis on the collected image, it must first extract the screen display area before subsequent inspections can be performed.

[0050] In actual applications, the area captured by the image collector is generally not the predetermined detection area, which leads to inaccurate subsequent detection results, and is prone to missed detection or over-detection. Therefore, the present application first obtains the effective edge in the current image according to the position of the image collector, and then translates the effective edge according to the current image collector position and the size of the predetermined detection area. After the translation, the area determined by the four edges is the predetermined detection area. The whole process is simple and efficient, and can accurately locate the predetermined detection area, which helps to improve the accuracy of defect detection and is less likely to miss detection. The following is a detailed description of the positioning device, positioning method, positioning system and corresponding storage medium of the LCD screen detection area of ​​the present application embodiment in combination with the accompanying drawings:

[0051] like Figure 2As shown in the figure, the positioning device for the liquid crystal display (LCD) panel detection area includes a collector, a display, and a controller. Among them, at least one collector is provided, and the collector is used to collect images of the product to be tested; the display is used to display the user interface; the controller is used to perform the operation of positioning the predetermined detection area. The above-mentioned positioning device for the LCD panel detection area can be used in the case of a single collector. At this time, the size of the product to be tested should be small. It can also be applied to the case where a single collector collects different areas of the product to be tested by moving. At this time, no specific limitation is imposed on the size of the product to be tested. It is also applicable to the case where multiple collectors collect the same product to be tested simultaneously. At this time, it is also applicable to products to be tested of any size. The following takes the example of four collectors collecting images simultaneously for detailed description.

[0052] As Figure 2 shown, the product to be tested is horizontally placed in a suitable lighting fixture. Four collectors are arranged in a two-row and two-column manner directly above the product to be tested, and the area collected by each collector is one-fourth of the product to be tested. Among them, the collector is a structure such as an industrial camera that can collect images of the product to be tested. The controller is connected to the collector and is used to perform the following operations:

[0053] Receive the first image including the first frame, and identify the four sides of the first frame. Taking the Figure 3 first image shown as an example, the four sides of the first frame identified by the controller are the Figure 3 four sides corresponding to 1, 2, 3, and 4 in the figure, and the area in the first frame corresponds to the first area of the product to be tested.

[0054] It should be noted that after obtaining the first image, the mean value of the first image is collected and used as a threshold to perform threshold segmentation on the first image. At this time, the area enclosed by the first frame can be obtained, and then the four sides in the first frame are obtained by the method of least squares linear fitting.

[0055] After that, the controller determines the first effective side and the second effective side among the four sides in the first image according to the position of the first area in the product to be tested. The first effective side and the second effective side correspond to the real boundary of the product to be tested. Among them, taking the Figure 3 figure as an example, Figure 3 in the figure, the sides corresponding to 2 and 3 are the real sides of the product to be tested, and the first area in the first image corresponds to the lower left corner of the product to be tested. Therefore, the side corresponding to 2 is set as the first effective side, and the side corresponding to 3 is set as the second effective side.

[0056] Translate the first effective edge to obtain the corresponding third corrected edge; translate the second effective edge to obtain the fourth corrected edge. The moving distances of the first effective edge and the second effective edge are both determined according to the preset size of the first region. For example, when four collectors are arranged in a two-row and two-column manner directly above the product to be tested, since the area collected by each collector is one-fourth of the product to be tested, the first effective edge needs to be moved by half of the length of the product to be tested in that direction towards the non-effective edge; the second effective edge needs to be moved by half of the length of the product to be tested in that direction towards the non-effective edge. The first effective edge, the second effective edge, the third corrected edge, and the fourth corrected edge can form a second frame. The second frame is rectangular, and the area enclosed by the second frame is the effective area. The effective area is used to represent the predetermined detection area of the product to be tested.

[0057] Among them, still taking the first image in Figure 3 as an example, when translating the first effective edge and the second effective edge, the first effective edge and the second effective edge can be moved sequentially, as shown in Figure 4A . At this time, the first effective edge, the second effective edge, the third corrected edge, and the fourth corrected edge are connected in sequence to form a second frame; the first effective edge and the second effective edge can also be moved simultaneously, as shown in Figure 4B . At this time, the enclosed area of the first effective edge, the second effective edge, the third corrected edge, and the fourth corrected edge is the effective area, and the first effective edge, the second effective edge, the third corrected edge, and the fourth corrected edge form a second frame. The effective area is used to represent the predetermined detection area of the product to be tested. The determination method of the predetermined detection area is simple and efficient, and helps to improve the accuracy of the subsequent detection results of the liquid crystal screen.

[0058] It can be understood that the process of judging the first effective edge and the second effective edge can be input after manual recognition or can be executed by the controller for recognition. As shown in Figure 5 , in some embodiments, it is preset that the sorting method of multiple first images is from left to right first, and then from top to bottom. The controller determines the position of the first image to be located according to the sorting method. The position of the first image to be located is the position of the first region in the product to be tested. The following elaborates on the method by which the controller determines the position of the first image to be located according to the sorting method of the first images.

[0059] Number the multiple first images with Arabic numerals according to the sorting method of the first images from left to right first, and then from top to bottom. The controller obtains the number of the first image to be located according to the above sorting method of the first images. As shown in Figure 5 , then according to the sorting method of all the first images, determine the relationship between the number corresponding to any first image and its row and column, and obtain the position of the first image to be located based on the relationship. For example, in some embodiments, refer to Figure 5, the first images are arranged in two rows, and the numbers corresponding to the four first images after being sorted according to the above sorting method are 0, 1, 2, and 3 respectively. The controller identifies the number M of the first image to be located, then calculates (M + 1) / 2, obtains the resulting value and the remainder, and determines the position of the current first image to be located according to the obtained resulting value and the remainder.

[0060] It can be understood that when the resulting value is less than or equal to 1, the current first image to be located is in the first row. At this time, when the remainder is not 0, the current first image to be located is in the first column of the first row; when the remainder is 0, the current first image to be located is in the second column of the first row. When the resulting value is greater than 1, the current first image to be located is in the second row. At this time, when the remainder is not 0, the current first image to be located is in the first column of the second row; when the remainder is 0, the current first image to be located is in the second column of the second row.

[0061] For example, when M is 0, since the resulting value is 0.5, less than 1, and the remainder is 1, the first image to be located is in the first column of the first row. At this time, the first effective side is the left side and the upper side of the first frame. When M is 1, since the resulting value is 1 and the remainder is 0, the first image to be located is in the second column of the first row. At this time, the first effective side is the right side and the upper side of the first frame. When M is 2, since the resulting value is 1.5, greater than 1, and the remainder is 1, the first image to be located is in the first column of the second row. At this time, the first effective side is the left side and the lower side of the first frame. When M is 3, since the resulting value is 2 and the remainder is 0, the first image to be located is in the second column of the second row. At this time, the first effective side is the right side and the lower side of the first frame.

[0062] In some embodiments, after obtaining the second frame, the controller is further configured to remove the non-effective regions in the first image by filling the regions outside the second frame in the first image with 0 gray level, so that only the effective regions are displayed in the first image. It can be understood that in this embodiment, the method of removing the non-effective regions is not specifically limited.

[0063] Since there is a situation where the first frame in the first image is skewed, in some embodiments, the controller can also obtain the four vertex coordinates of the second frame and perform an affine transformation on the vertex coordinates to stretch the effective region into a standard rectangular region. At this time, the effective region is translated to the middle position of the first image, which is helpful for conveniently detecting the first image.

[0064] Based on the introduction of the positioning device solution for the liquid crystal display detection region and the related drawings in the above text, the present application also provides a method for positioning the liquid crystal display detection region, in combination with Figure 6 and Figure 7As shown in the figure, the positioning method for the liquid crystal screen detection area includes the following steps:

[0065] In step 100, a test sample such as a liquid crystal screen is placed in a lighting fixture, and a collector is installed above the lighting fixture. The liquid crystal screen image is switched to a bright image through the lighting fixture, and the collector captures an image. The controller receives a first image including a first frame, as shown in Figure 7 Figure 7-1. Then, the four sides of the first frame are identified to obtain a white frame line as shown in Figure 7 Figure 7-3. The area in the first frame corresponds to the first area of the test sample, as shown in Figure 7 the area shown in Figure 7-2.

[0066] It can be understood that after obtaining the first image, the mean value of the first image is collected as a threshold to perform threshold segmentation on the first image. Then, the area enclosed by the first frame is obtained, and the four sides in the first frame are obtained by the method of least squares linear fitting.

[0067] In step 200, according to the position of the first area in the test sample, the first effective side and the second effective side among the four sides are determined. That is, according to the number of the current first image, the first effective side and the second effective side in the first frame are obtained. The schematic diagram of the result of this step is the white frame line as shown in Figure 7 Figure 7-4.

[0068] In some embodiments, it is preset that the sorting method of multiple first images is arranged first from left to right and then from top to bottom. The controller determines the position of the first image to be located according to the sorting method, and the position of the first image to be located is the position of the first area in the test sample.

[0069] Specifically, according to the sorting method of the first images, the number of the first image to be located is obtained; according to the sorting method of all first images, the relationship between the number corresponding to any first image and its row and column is determined, and the position of the first image to be located is obtained.

[0070] In step 300, the first effective side and the second effective side are translated in the direction of the non-effective side to obtain corresponding third corrected sides and fourth corrected sides to form a second frame. The moving distances of the first effective side and the second effective side are both determined according to the preset size of the first area. Among them, the second frame is a rectangle, and the area enclosed by the second frame is the effective area, as shown in Figure 7 Figure 7-5, Figure 7 the white frame in Figure 7-5 is the second frame, and the effective area is used to represent the predetermined detection area of the test sample.

[0071] In some embodiments, as shown in Figure 8 Figure, it is filled with 0 gray value Figure 8the outer area of the second frame within the first image in 8-1, to remove the invalid area in the first image, so that only the valid area is displayed in the first image, as shown in Figure 8 shown in 8-2. In some other embodiments, the four vertex coordinates of the valid area are obtained, where the four vertices are the intersections of pairwise intersections between the first valid edge, the second valid edge, the third corrected edge, and the fourth corrected edge, and an affine transformation is performed on the vertex coordinates to stretch the valid area into a standard rectangular area. At this time, the valid area is translated to the middle position of the first image, see Figure 8 shown in 8-3.

[0072] It should be noted that multiple first images after affine transformation can be stitched into a complete image. At this time, since the valid areas in each first image are consistent with the corresponding predetermined detection areas, the entire stitched image is also relatively accurate, which helps the subsequent accurate detection of the liquid crystal display screen and other test items.

[0073] Figure 9 is a schematic structural diagram of a positioning system for a liquid crystal display screen detection area provided by an embodiment of the present application, as shown in Figure 9 shown. The positioning system for the liquid crystal display screen detection area provided by the embodiment of the present application includes a first frame recognition module, a valid edge recognition module, and a second frame recognition module. Among them, the first frame recognition module is used to receive a first image including a first frame and recognize the four edges of the first frame; the area in the first frame corresponds to the first area of the test item. The valid edge recognition module is used to determine the first valid edge and the second valid edge among the four edges according to the position of the first area in the test item; the second frame recognition module is used to translate the first valid edge and the second valid edge to obtain the corresponding third corrected edge and fourth corrected edge to form a second frame, and the moving distances of the first valid edge and the second valid edge are both determined according to the preset size of the first area. Among them, the area enclosed by the second frame is the valid area, and the valid area is used to represent the predetermined detection area of the test item.

[0074] In some embodiments, the valid edge recognition module is further used to, when the number of first images is multiple, preset the sorting method of the multiple first images to be arranged first from left to right and then from top to bottom, and determine the position of the first image to be located according to the sorting method. The position of the first image to be located is the position of the first area in the test item.

[0075] In some embodiments, the valid edge recognition module is further used to obtain the number of the first image to be located according to the sorting method of the first images;

[0076] According to the sorting method of all the first images, determine the relationship between the number corresponding to any first image and its row and column, and obtain the position of the first image to be located.

[0077] In some embodiments, such as Figure 10 shown, the positioning system for the liquid crystal display detection area further includes a region removal module and an affine transformation module. The region removal module is used to remove the invalid regions in the first image so that only the valid regions are displayed in the first image. The affine transformation module is used to obtain the four vertex coordinates of the valid region and perform an affine transformation on the vertex coordinates to stretch the valid region into a standard rectangular region. At this time, the valid region is translated to the middle position of the first image.

[0078] It should be noted that the above-mentioned region removal module and affine transformation module can exist independently or simultaneously.

[0079] Each module in the above system can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form so that the processor can call and execute the operations corresponding to each of the above modules.

[0080] The positioning system for the liquid crystal display detection area provided by the embodiments of the present application has a similar implementation principle and technical effect to the above method embodiments, and will not be elaborated here.

[0081] Figure 11 is a schematic structural diagram of a positioning device for the liquid crystal display detection area provided by the embodiments of the present application. As Figure 11 shown, in the third aspect, a positioning device for the liquid crystal display detection area provided by the embodiments of the present application includes a memory and a processor. The memory is used to store the positioning program for the liquid crystal display detection area, and the processor runs the positioning program for the liquid crystal display detection area so that the positioning device for the liquid crystal display detection area executes the above-mentioned positioning method for the liquid crystal display detection area.

[0082] In the fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores a positioning program for the liquid crystal display detection area. When the positioning program for the liquid crystal display detection area is executed by the processor, the above-mentioned positioning method for the liquid crystal display detection area is realized. The specific execution method is as follows:

[0083] In some embodiments, a first image including a first frame is received, and the four sides of the first frame are recognized; the area in the first frame corresponds to the first area of the product to be tested;

[0084] According to the position of the first area in the product to be tested, the first valid side and the second valid side among the four sides are determined;

[0085] The first valid side and the second valid side are translated to obtain the corresponding third corrected side and fourth corrected side to form a second frame. The moving distances of the first valid side and the second valid side are both determined according to the preset size of the first area;

[0086] Among them, the second frame is rectangular, and the area enclosed by the second frame is the effective area, which is used to represent the predetermined detection area of the product to be tested.

[0087] In some embodiments, when the number of the first images is multiple, the preset sorting method of the multiple first images is to arrange them from left to right first, and then from top to bottom. According to the sorting method, the position of the first image to be located is determined, and the position of the first image to be located is the position of the first area in the product to be tested.

[0088] In some embodiments, according to the sorting method of the first images, the number of the first image to be located is obtained.

[0089] According to the sorting method of all the first images, the relationship between the number corresponding to any first image and its row and column is determined to obtain the position of the first image to be located.

[0090] In some embodiments, the non-effective area in the first image is removed so that only the effective area is displayed in the first image.

[0091] In some embodiments, the four vertex coordinates of the second frame are obtained, and an affine transformation is performed on the vertex coordinates to stretch the effective area into a standard rectangular area. At this time, the effective area is translated to the middle position of the first image.

[0092] The beneficial effect of the embodiments in this part is that by identifying the first effective edge and the second effective edge in the first frame, and moving the first effective edge and the second effective edge according to the preset size of the first area, the corresponding third corrected edge and fourth corrected edge are obtained, so that the first effective edge, the second effective edge, the third corrected edge and the fourth corrected edge form the second frame, and the area enclosed by the second frame is the effective area, which can be used to accurately represent the predetermined detection area of the product to be tested. At this time, each first image can be an accurate area to be detected, which helps to accurately detect the product to be tested such as the liquid crystal display screen subsequently.

[0093] Furthermore, by removing the non-effective area in the first image so that only the effective area is displayed in the first image, the subsequent detection area can be reduced, which helps to improve the detection accuracy of the product to be tested such as the liquid crystal display screen subsequently.

[0094] Furthermore, by obtaining the four vertex coordinates of the second frame and performing an affine transformation on the vertex coordinates to stretch the effective area into a standard rectangular area, and at this time, the effective area is translated to the middle position of the first image, it helps to facilitate the subsequent detection.

[0095] For the sake of convenience in explanation, the above description has been made in connection with specific embodiments. However, the discussion in some of the above embodiments is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. Various modifications and variations can be derived according to the above teachings. The selection and description of the above embodiments are for the purpose of better explaining the principles and actual applications, so that those skilled in the art can better use the embodiments and various different modified embodiments suitable for specific use considerations.

Claims

1. A positioning device for a liquid crystal screen detection area, characterized in that, the device includes: A collector, set to at least one, and the collector is used to collect an image of a product to be tested; A display, used to display a user interface; A controller, configured to: Receive a first image including a first frame, and identify four sides of the first frame; the area in the first frame corresponds to a first area of the product to be tested; Determine a first effective side and a second effective side among the four sides according to the position of the first area in the product to be tested; Translate the first effective side and the second effective side to obtain corresponding third corrected sides and fourth corrected sides to form a second frame, and the moving distances of the first effective side and the second effective side are both determined according to a preset size of the first area; Wherein, the area enclosed by the second frame is an effective area, and the effective area is used to represent a predetermined detection area of the product to be tested.

2. The positioning device for a liquid crystal screen detection area according to claim 1, characterized in that, The determining the first effective side and the second effective side among the four sides according to the position of the first area in the product to be tested further includes: When the number of the first images is multiple, a sorting method of the multiple first images is preset to be arranged first from left to right and then from top to bottom, and the controller is configured to: determine the position of the first image to be positioned according to the sorting method, and the position of the first image to be positioned is the position of the first area in the product to be tested.

3. The positioning device for a liquid crystal screen detection area according to claim 2, characterized in that, For the determining the position of the first image to be positioned according to the sorting method, the controller is further configured to: Obtain the number of the first image to be positioned according to the sorting method of the first image; Determine the relationship between the number corresponding to any first image and its row and column according to the sorting method of all the first images to obtain the position of the first image to be positioned.

4. The positioning device for a liquid crystal screen detection area according to claim 1, characterized in that, For the translating the first effective side and the second effective side to obtain corresponding third corrected sides and fourth corrected sides to form a second frame, the controller is further configured to: Remove the non-effective area in the first image so that only the effective area is displayed in the first image.

5. The positioning device for a liquid crystal screen detection area according to any one of claims 1-4, characterized in that, For the translating the first effective side and the second effective side to obtain corresponding third corrected sides and fourth corrected sides to form a second frame, the controller is further configured to: Obtain the four vertex coordinates of the second frame, and perform an affine transformation on the vertex coordinates to stretch the effective area into a standard rectangular area. At this time, the effective area is translated to the middle position of the first image.

6. A positioning method for a liquid crystal screen detection area, characterized in that, the method includes: Receive a first image including a first frame, and identify four sides of the first frame; the area in the first frame corresponds to a first area of the product to be tested; Determine a first effective side and a second effective side among the four sides according to the position of the first region in the product to be tested; Translate the first effective side and the second effective side to obtain corresponding third corrected sides and fourth corrected sides to form a second frame, and the moving distances of the first effective side and the second effective side are both determined according to the preset size of the first region; Wherein, the region enclosed by the second frame is an effective region, and the effective region is used to represent the predetermined detection region of the product to be tested.

7. The method for positioning a liquid crystal display detection region according to claim 6, characterized in that The determining the first effective side and the second effective side among the four sides according to the position of the first region in the product to be tested further includes: When the number of the first images is multiple, preset the sorting method of the multiple first images to be arranged first from left to right and then from top to bottom, and determine the position of the first image to be located according to the sorting method, and the position of the first image to be located is the position of the first region in the product to be tested.

8. The method for positioning a liquid crystal display detection region according to claim 7, characterized in that The determining the position of the first image to be located according to the sorting method further includes: Obtain the number of the first image to be located according to the sorting method of the first image; According to the sorting method of all the first images, determine the relationship between the number corresponding to any first image and its row and column where it is located, and obtain the position of the first image to be located.

9. The method for positioning a liquid crystal display detection region according to claim 6, characterized in that The translating the first effective side and the second effective side to obtain corresponding third corrected sides and fourth corrected sides to form a second frame further includes: Remove the non-effective regions in the first image so that only the effective regions are displayed in the first image.

10. The method for positioning a liquid crystal display detection region according to any one of claims 6-9, characterized in that The translating the first effective side and the second effective side to obtain corresponding third corrected sides and fourth corrected sides to form a second frame further includes: Obtain the four vertex coordinates of the effective region, and perform an affine transformation on the vertex coordinates to stretch the effective region into a standard rectangular region. At this time, the effective region is translated to the middle position of the first image.

Images