CN115494659A - Liquid crystal panel detection method and system - Google Patents

Abstract

The invention relates to a liquid crystal panel detection method and system, the detection method is used to realize the edge detection or/and defect detection of the liquid crystal panel; wherein, the edge detection includes the following steps: acquiring the measurement result image of the liquid crystal panel to be tested; extracting the measurement result An area of interest in the image; obtaining angular coordinate points and/or edge profiles in the area of interest of the measurement result image; measuring the grinding accuracy of the liquid crystal panel to be tested according to the edge profile to obtain a grinding accuracy detection result; and/or, according to the edge profile Measure the cutting accuracy of the liquid crystal panel to be tested to obtain the cutting accuracy detection result; and/or measure the chamfering accuracy of the liquid crystal panel to be tested according to the corner coordinate points and the edge profile to obtain the chamfering accuracy detection result; output and store the grinding precision detection result And/or cutting accuracy detection results and/or chamfering accuracy detection results; the present invention improves the efficiency of edge detection and defect detection and the stability of detection results.

Description

Method and system for detecting a liquid crystal panel

technical field

The invention relates to the technical field of liquid crystal panel detection, in particular to a liquid crystal panel detection method and system.

Background technique

At present, the detection of LCD panels includes two parts: edge measurement and defect detection. It mainly relies on manual measurement of the corresponding size of the edge of the screen, and then relies on human eyes to judge defects. Edge measurement mainly includes three parts: grinding measurement, cutting measurement and chamfering measurement. At present, the manual measurement method adopted by the factory is mainly to measure under the microscope. Grinding measurement is to take multiple points in the grinding area of the screen at a specified position or a random position, and then measure the width of the grinding area; cutting measurement is to measure the distance from the edge of the screen to the upper and lower mark points; chamfering measurement is to measure the width of the grinding area. Measure the chamfers of the upper left corner, lower left corner, upper right corner, and lower right corner of the screen. The detection is time-consuming and labor-intensive, and the accuracy of the detection results of manual detection is related to the experience of the detection personnel, which affects the accuracy of the final detection results.

Defect detection is mainly to detect four types of defects such as gaps, breakages, cracks and protrusions. At present, the defect detection method adopted by the factory mainly uses human eye observation to find out whether these four types of defects exist on the screen in turn. This method of manual measurement and defect detection is time-consuming, labor-intensive, inefficient, cumbersome, highly subjective, and affected by personnel emotions, vision, ambient light, and inconsistent judgment standards of different human eyes.

Contents of the invention

In order to solve the technical problem of poor stability and inconsistency in detection results of edge measurement and defect detection and storage of liquid crystal panels in the prior art, the present invention provides a liquid crystal panel detection method and system.

The technical scheme that the present invention solves the problems of the technologies described above is as follows:

A detection method of a liquid crystal panel, the detection method is used to realize the edge detection or/and defect detection of the liquid crystal panel; wherein, the edge detection comprises the following steps:

Obtain a measurement result image of the liquid crystal panel to be tested;

extracting the region of interest of the measurement result image;

Obtaining corner coordinate points and/or edge contours in the region of interest of the measurement result image;

Measuring the grinding accuracy of the liquid crystal panel to be tested according to the edge profile to obtain a grinding accuracy detection result; and/or measuring the cutting accuracy of the liquid crystal panel to be tested according to the edge profile to obtain a cutting accuracy detection result; and/or Or, measuring the chamfering accuracy of the liquid crystal panel to be tested according to the corner coordinate points and the edge profile to obtain a chamfering accuracy detection result;

Outputting and storing the grinding accuracy inspection result and/or the cutting accuracy inspection result and/or the chamfering accuracy inspection result.

The beneficial effects of the present invention are: by determining the edge and corner coordinate points in the measurement result image of the liquid crystal panel to be tested, measuring the parameters such as the edge size of the liquid crystal panel to be tested, it is convenient to improve the efficiency of edge detection and the stability of the detection result .

On the basis of the above technical solutions, the present invention can also be improved as follows.

Further, the defect detection includes the following steps:

Extracting the edge defect image of the liquid crystal panel to be tested in the measurement result image;

Classifying the edge defect image of the liquid crystal panel to be tested by comparing the edge defect image of the liquid crystal panel to be tested with a defect comparison model; wherein, the defect comparison model is a computer vision recognition model;

Outputting and storing the classified edge defect images of the liquid crystal panel to be tested.

Further, by comparing the image of the edge defect of the liquid crystal panel to be tested with a defect comparison model, the image of the edge defect of the liquid crystal panel to be tested is classified; specifically, the steps are as follows:

Build computer vision models;

Using various types of liquid crystal panel edge defect sample data to perform model training on the computer vision model to obtain a variety of defect comparison models;

Comparing the image of the edge defect of the liquid crystal panel to be tested with a variety of defect comparison models to obtain a variety of edge defect images of the liquid crystal panel to be tested corresponding to the defect comparison model;

Classifying all the edge defect images of the liquid crystal panel to be tested.

The beneficial effect of adopting the above further solution is that by comparing the edge defect image of the liquid crystal panel to be tested with the defect comparison model, the preset defects in the model can be identified, and the edge defects can be automatically identified through the computer vision recognition method, which improves the identification efficiency. At the same time, the recognition standard is also unified, and the stability of the detection result of the liquid crystal panel is improved.

Further, storing the edge detection result and the classified image of the edge defect of the liquid crystal panel to be tested specifically includes the following steps:

storing the edge detection result;

The classified edge defect images of the liquid crystal panel to be tested are respectively stored by category.

Further, extracting the region of interest of the measurement result image specifically includes the following steps:

Obtaining the boundary of the liquid crystal panel to be tested in the measurement result image;

determining the outer frame of the liquid crystal panel to be tested in the measurement result image by screening the boundary of the liquid crystal panel to be tested in the measurement result image;

determining the region of interest according to the outer frame of the liquid crystal panel to be tested;

Or, extracting the region of interest of the measurement result image specifically includes the following steps:

extracting the background area of the measurement result image;

The region of interest is determined by performing region screening on the measurement result image by using the preset background region area, the preset background region width value and the preset background region height value.

The beneficial effect of adopting the above-mentioned further scheme is that the region of interest of the measurement result image can be determined by screening the boundary of the liquid crystal panel to be tested to improve the detection versatility of the liquid crystal panel when the size of the liquid crystal panel is different; The area of the background area, the preset background area width value and the preset background area height value perform area screening on the measurement result image, so that batch-produced liquid crystal panels of the same type can be uniformly processed to improve detection efficiency.

Further, measuring the grinding precision of the liquid crystal panel to be tested according to the edge profile of the liquid crystal panel to be tested to obtain a grinding precision detection result, specifically comprising the following steps:

Obtaining a binary image of the measurement result image based on a threshold segmentation method;

Based on the straight line fitting method, according to the edge profile of the liquid crystal panel to be tested, the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested in the binary image of the measurement result image are obtained;

Calculate the distance between the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested to obtain the grinding width value;

Calculate the area between the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested to obtain the grinding area value;

Calculating the rectangularity of the rectangular area corresponding to the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested, to obtain the grinding rectangularity value;

Calculate the height of the area between the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested to obtain the grinding height value;

Wherein, the grinding accuracy detection result includes the grinding width value, the grinding area value, the grinding squareness value and the grinding height value.

The beneficial effect of adopting the above further solution is that the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested are obtained by the straight line fitting method, which can increase the amount of data for detection and calculation, and the detection result can be closer to the actual boundary line, which improves the detection accuracy.

Further, calculating the distance between the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested, to obtain the grinding width value, specifically includes the following steps:

Segmenting the grinding area of the liquid crystal panel to be tested in the binary image to obtain a plurality of segmented grinding areas;

Calculating the width values of the boundary lines on both sides of the grinding area in each segmented grinding area;

The value of the grinding width is obtained by averaging the width values of the boundary lines on both sides of the grinding area in all segmented grinding areas.

The beneficial effect of adopting the above further solution is that the accuracy of the detection result can be improved by segment detection and averaging.

Further, measuring the cutting precision of the liquid crystal panel to be tested according to the edge profile of the liquid crystal panel to be tested, and obtaining a cutting precision detection result, comprises the following steps:

When there are upper and lower cross Mark points on the measurement result figure, connect the upper and lower cross Mark points, calculate the distance from any point on the edge contour to the connection line, and obtain the cutting accuracy value; When there is no cross mark point or only one cross mark point on the measurement result map, determine any target point on the edge contour, identify the corresponding mark position of any target point on the edge contour on the measurement result map, and calculate The distance from any target point on the edge profile to the corresponding mark position is used to obtain the cutting accuracy value;

Wherein, the cutting accuracy detection result includes the cutting accuracy value.

Further, measuring the chamfering precision of the liquid crystal panel to be tested according to the corner coordinate points and the edge profile of the liquid crystal panel to be tested, to obtain a chamfering precision detection result, comprising the following steps:

Using an adaptive threshold algorithm to obtain the chamfering feature flag in the region of interest of the measurement result image, and determine the chamfering detection area;

Segmenting and extracting the chamfering detection area to obtain an image of the chamfering area;

According to the preset chamfer area characteristic value, the preset chamfer width characteristic value and the preset chamfer height characteristic value, filter out the final chamfer image in the chamfer area image;

determining the minimum circumscribed rectangle of the final chamfer according to the corner coordinate points and the edge profile;

calculating a final chamfer width value and a final chamfer height value of the final chamfer according to the minimum circumscribed rectangle of the final chamfer;

Wherein, the chamfering accuracy detection result includes the final chamfering width value and the final chamfering height value

In order to solve the above technical problems, the present invention also provides the following technical solutions:

A detection system for a liquid crystal panel, the detection system is used to perform edge detection or/and defect detection on the liquid crystal panel; wherein, the edge detection system includes,

A data acquisition module, configured to acquire a measurement result image of the liquid crystal panel to be tested;

A data processing module, configured to extract the region of interest of the measurement result image, and obtain corner coordinate points and/or edge contours in the measurement result image;

an accuracy detection module, configured to measure the grinding accuracy of the liquid crystal panel to be tested according to the edge profile, and obtain a grinding accuracy detection result; and/or, used to measure the cutting accuracy of the liquid crystal panel to be tested according to the edge profile, Obtaining a cutting accuracy detection result; and/or, measuring the chamfering accuracy of the liquid crystal panel to be tested according to the corner coordinate points and the edge profile to obtain a chamfering accuracy detection result;

An output module, configured to output the testing results of the grinding accuracy and/or the testing results of the cutting accuracy and/or the testing results of the chamfering accuracy;

The storage module is used for storing the grinding accuracy detection result and/or the cutting accuracy detection result and/or the chamfering accuracy detection result.

Description of drawings

FIG. 1 is a flow chart of a detection method for a liquid crystal panel in an embodiment of the present invention.

detailed description

The principles and features of the present invention are described below in conjunction with the accompanying drawings, and the examples given are only used to explain the present invention, and are not intended to limit the scope of the present invention.

Example 1

As shown in FIG. 1, the present embodiment provides a detection method of a liquid crystal panel, and the detection method is used to realize edge detection or/and defect detection of the liquid crystal panel; wherein, the edge detection includes the following steps:

S1. Obtain the measurement result image of the liquid crystal panel to be tested;

S2. Extracting the region of interest of the measurement result image; the specific steps are: obtaining the boundary of the liquid crystal panel to be tested in the measurement result image;

Determining the outer frame of the liquid crystal panel to be tested in the measurement result image by screening the boundary of the liquid crystal panel to be tested in the measurement result image;

Determine the region of interest according to the outer frame of the liquid crystal panel to be tested;

Alternatively, the specific steps are:

Using the area of the preset background area, the width value of the preset background area and the height value of the preset background area to filter the area of the measurement result image to determine the area of interest. If the region of interest is inaccurate, the problem can be solved by increasing the threshold parameter.

S3. Acquire corner coordinate points and/or edge contours in the region of interest of the measurement result image.

S4. Measure the grinding accuracy of the liquid crystal panel to be tested according to the edge profile to obtain a grinding accuracy detection result; and/or measure the cutting accuracy of the liquid crystal panel to be tested according to the edge profile to obtain a cutting accuracy detection result; And/or, measure the chamfering precision of the liquid crystal panel to be tested according to the corner coordinate points and the edge profile, and obtain the chamfering precision detection result; specifically, measure the grinding precision of the liquid crystal panel to be tested according to the edge profile of the liquid crystal panel to be tested, Obtaining the grinding accuracy detection result includes the following steps:

Based on the threshold segmentation method, the binary image of the measurement result image is obtained;

Based on the straight line fitting method, the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested in the binary image of the measurement result image are obtained;

Calculate the distance between the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested to obtain the grinding width value;

Calculate the area between the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested to obtain the grinding area value;

Calculate the rectangularity of the rectangular area corresponding to the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested, to obtain the grinding rectangularity value;

Calculate the height of the area between the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested to obtain the grinding height value.

Calculate the distance between the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested to obtain the grinding width value, including the following steps:

Segmenting the grinding area of the liquid crystal panel to be tested in the binary image to obtain a plurality of segmented grinding areas;

Calculating the width values of the boundary lines on both sides of the grinding area in each segmented grinding area;

Average the width values of the boundary lines on both sides of the grinding area in all segmented grinding areas to obtain the grinding width value.

Wherein, the grinding accuracy detection result includes the grinding width value, the grinding area value, the grinding squareness value and the grinding height value.

Measuring the cutting precision of the liquid crystal panel to be tested according to the edge profile of the liquid crystal panel to be tested to obtain a cutting precision test result, including the following steps:

When there are upper and lower cross Mark points on the measurement result graph, connect the upper and lower cross Mark points, calculate the distance from any point on the edge contour to the connecting line, and obtain the cutting accuracy value; when there is no cross mark on the measurement result graph When there is only one Mark point or only one cross Mark point, determine any target point on the edge contour, identify the mark position corresponding to any target point on the edge contour on the measurement result map, and calculate the distance from any target point on the edge contour to the corresponding mark position, Get the cutting precision value. Wherein, the cutting accuracy detection result includes the cutting accuracy value.

Measuring the chamfering accuracy of the liquid crystal panel to be tested according to the corner coordinate points and the edge profile of the liquid crystal panel to be tested includes the following steps:

Using an adaptive threshold algorithm to obtain the chamfering feature flag in the region of interest of the measurement result image, and determine the chamfering detection area;

Segmenting and extracting the chamfering detection area to obtain an image of the chamfering area;

According to the preset chamfer area characteristic value, the preset chamfer width characteristic value and the preset chamfer height characteristic value, filter out the final chamfer image in the chamfer area image;

determining the minimum circumscribed rectangle of the final chamfer according to the corner coordinate points and the edge profile;

calculating a final chamfer width value and a final chamfer height value of the final chamfer according to the minimum circumscribed rectangle of the final chamfer;

Wherein, the chamfering accuracy detection result includes the final chamfering width value and the final chamfering height value.

S5. Output and store the grinding accuracy detection result and/or cutting accuracy detection result and/or chamfering accuracy detection result.

Example 2

Based on Embodiment 1, this embodiment provides a detection method of a liquid crystal panel, and the detection method is used to realize edge detection or/and defect detection of the liquid crystal panel; wherein, the defect detection includes the following steps:

S10. Extracting the edge defect image of the liquid crystal panel to be tested in the measurement result image;

S11. By comparing the edge defect image of the liquid crystal panel to be tested with the defect comparison model, classify the edge defect image of the liquid crystal panel to be tested; wherein, the defect comparison model is a computer vision recognition model; specifically includes the following steps:

Build computer vision models;

Use various types of liquid crystal panel edge defect sample data to train the computer vision model to obtain a variety of defect comparison models; among them, the various types of liquid crystal panel edge defect sample data include at least gap sample data, damaged sample data, and crack samples data and bump sample data;

Comparing the edge defect images of the liquid crystal panel to be tested with various defect comparison models respectively, and obtaining various edge defect images of the liquid crystal panel to be tested corresponding to the defect comparison models;

Classify all the edge defect images of the liquid crystal panel to be tested.

Among them, the method of obtaining the image of the edge defect of the liquid crystal panel to be tested is the adaptive threshold method; the idea of the adaptive threshold is not to calculate the threshold of the global image, but to calculate the local threshold according to the brightness distribution of different regions of the image, so for different regions of the image, It can adaptively calculate different thresholds, so it is called the adaptive threshold method, which is suitable for defect segmentation of images with uneven gray levels; the algorithm assumes that image pixels can be divided into background and target according to the threshold. Then, the optimal threshold is calculated to distinguish the two types of pixels, so that the two types of pixels have the greatest degree of discrimination. Its specific calculation formula is as follows:

N ₁ +N ₂ =M×N

ω ₁ +ω ₂ =1

μ＝μ ₁ ×ω ₁ +μ ₂ ×ω ₂

g＝ω ₁ ×(μ-μ ₁ ) ² +ω ₂ ×(μ-μ ₂ ) ²

N ₁ represents the number of pixels whose grayscale is greater than the segmentation threshold of the target and background; N ₂ represents the number of pixels whose grayscale is smaller than the segmentation threshold of the target and background; M×N represents the size of the image; ω ₁ represents the number of target pixels The proportion of the entire image; _ω2 represents the proportion of the background pixel points to the entire image; μ1 represents the average gray level of the target pixel; μ2 represents the average gray level _of the background pixel; μ represents the total average gray value of the image; _g represents the class Variance between.

S12. Outputting the classified images of edge defects of the liquid crystal panel to be tested;

S13. Storing the classified edge defect images of the liquid crystal panel to be tested; specifically including the following steps: storing the classified edge defect images of the liquid crystal panel to be tested by category.

In this embodiment, by comparing the edge defect image of the liquid crystal panel to be tested with the defect comparison model, the preset defects in the model are identified, and the edge defects are automatically identified through the computer vision recognition method, which improves the recognition efficiency and unifies the recognition standards. , improving the stability of the detection result of the liquid crystal panel.

Example 3

Based on Embodiment 1, this embodiment provides a detection system for a liquid crystal panel, including a data acquisition module, a data processing module, an accuracy detection module, a defect detection module, an output module, and a storage module.

A data acquisition module, configured to acquire a measurement result image of the liquid crystal panel to be tested;

A data processing module, configured to extract the region of interest of the measurement result image, and obtain the corner coordinate points and/or edge contours of the liquid crystal panel to be tested in the measurement result image;

A precision detection module, configured to measure the grinding precision of the liquid crystal panel to be tested according to the edge profile of the liquid crystal panel to be tested, to obtain a grinding precision detection result; and/or, to measure according to the edge profile of the liquid crystal panel to be tested The cutting accuracy of the liquid crystal panel to be measured is obtained to obtain a cutting accuracy detection result; and/or, it is used to measure the chamfering accuracy of the liquid crystal panel to be measured according to the corner coordinate points and edge contours of the liquid crystal panel to be measured to obtain the chamfering accuracy of the liquid crystal panel to be measured. Angular accuracy test results;

The defect detection module is used to extract the edge defect image of the liquid crystal panel to be tested in the measurement result image; by comparing the edge defect image of the liquid crystal panel to be tested with the defect comparison model, the edge defect of the liquid crystal panel to be tested The images are classified; wherein, the defect comparison model is a computer vision recognition model;

An output module, configured to output a grinding accuracy test result and/or a cutting accuracy test result and/or a chamfering accuracy test result and/or a classified edge defect image of the liquid crystal panel to be tested;

The storage module is used for storing the grinding accuracy detection result and/or the cutting accuracy detection result and/or the chamfering accuracy detection result and/or the classified edge defect images of the liquid crystal panel to be tested.

Specifically, the above-mentioned data acquisition module, data processing module, accuracy detection module, defect detection module and output module are all computer programs or a collection of function codes in computer programs; the storage module can be computer memory, internal memory, flash memory and external storage equipment etc.

The embodiment of the present invention obtains the measurement result image of the liquid crystal panel to be tested by using a computer program, and determines the edges and corner coordinate points in the measurement result image of the liquid crystal panel to be tested, and measures parameters such as the edge size of the liquid crystal panel to be tested. In terms of detection, the efficiency of edge detection and the stability of detection results are improved; by comparing the image of the edge defect of the liquid crystal panel to be tested with the defect comparison model, the preset defects in the model are identified, and the edge is automatically recognized by the computer vision recognition method. Defects improve the identification efficiency, and at the same time unify the identification standards and improve the stability of the detection results of the liquid crystal panel.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the concept and principles of the present invention shall be included in the protection of the present invention. within range.

Claims (10)

1. a detection method of liquid crystal panel, it is characterized in that, described detection method is used for realizing the edge detection of liquid crystal panel or/and defect detection; Wherein, described edge detection comprises the steps: Obtain a measurement result image of the liquid crystal panel to be tested; extracting the region of interest of the measurement result image; Obtaining corner coordinate points and/or edge contours in the region of interest of the measurement result image; Measuring the grinding accuracy of the liquid crystal panel to be tested according to the edge profile to obtain a grinding accuracy detection result; and/or measuring the cutting accuracy of the liquid crystal panel to be tested according to the edge profile to obtain a cutting accuracy detection result; and/or Or, measuring the chamfering accuracy of the liquid crystal panel to be tested according to the corner coordinate points and the edge profile to obtain a chamfering accuracy detection result; Outputting and storing the grinding accuracy inspection result and/or the cutting accuracy inspection result and/or the chamfering accuracy inspection result. 2. the detection method of liquid crystal panel according to claim 1, is characterized in that, described defect detection comprises the steps: Extracting the edge defect image of the liquid crystal panel to be tested in the measurement result image; Classifying the edge defect image of the liquid crystal panel to be tested by comparing the edge defect image of the liquid crystal panel to be tested with a defect comparison model; wherein, the defect comparison model is a computer vision recognition model; Outputting and storing the classified edge defect images of the liquid crystal panel to be tested. 3. the detection method of liquid crystal panel according to claim 2, it is characterized in that, by comparing the edge defect image of described liquid crystal panel to be tested with defect comparison model, the edge defect image of described liquid crystal panel to be tested is classified, Specifically include the following steps: Build computer vision models; Using various types of liquid crystal panel edge defect sample data to perform model training on the computer vision model to obtain a variety of defect comparison models; Comparing the image of the edge defect of the liquid crystal panel to be tested with a variety of defect comparison models to obtain a variety of edge defect images of the liquid crystal panel to be tested corresponding to the defect comparison model; Classifying all the edge defect images of the liquid crystal panel to be tested. 4. the detection method of liquid crystal panel according to claim 3, is characterized in that, stores the edge defect image of described liquid crystal panel to be tested through classification, specifically comprises the steps: The classified edge defect images of the liquid crystal panel to be tested are respectively stored by category. 5. the detection method of liquid crystal panel according to claim 1, is characterized in that, extracting the region of interest of described measurement result image, specifically comprises the steps: Obtaining the boundary of the liquid crystal panel to be tested in the measurement result image; determining the outer frame of the liquid crystal panel to be tested in the measurement result image by screening the boundary of the liquid crystal panel to be tested in the measurement result image; determining the region of interest according to the outer frame of the liquid crystal panel to be tested; Or, extracting the region of interest of the measurement result image specifically includes the following steps: extracting the background area of the measurement result image; The region of interest is determined by performing region screening on the measurement result image by using the preset background region area, the preset background region width value and the preset background region height value. 6. The detection method of the liquid crystal panel according to claim 1 or 5, characterized in that, measuring the grinding accuracy of the liquid crystal panel to be tested according to the edge profile to obtain a grinding accuracy detection result, specifically comprising the following steps: Obtaining a binary image of the measurement result image based on a threshold segmentation method; Based on the straight line fitting method, according to the edge profile of the liquid crystal panel to be tested, the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested in the binary image of the measurement result image are obtained; Calculate the distance between the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested to obtain the grinding width value; Calculate the area between the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested to obtain the grinding area value; Calculating the rectangularity of the rectangular area corresponding to the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested, to obtain the grinding rectangularity value; Calculate the height of the area between the boundary lines on both sides of the grinding area of the liquid crystal panel to be tested to obtain the grinding height value; Wherein, the grinding accuracy detection result includes the grinding width value, the grinding area value, the grinding squareness value and the grinding height value. 7. the detection method of liquid crystal panel according to claim 6, is characterized in that, calculates the distance between the boundary lines on both sides of the grinding area of said liquid crystal panel to be measured, obtains the grinding width value, specifically comprises the steps: Segmenting the grinding area of the liquid crystal panel to be tested in the binary image to obtain a plurality of segmented grinding areas; Calculating the width values of the boundary lines on both sides of the grinding area in each segmented grinding area; The value of the grinding width is obtained by averaging the width values of the boundary lines on both sides of the grinding area in all segmented grinding areas. 8. The detection method of the liquid crystal panel according to claim 1 or 5, wherein measuring the cutting accuracy of the liquid crystal panel to be tested according to the edge profile to obtain a cutting accuracy detection result, specifically comprises the following steps: When there are upper and lower two cross Mark points on the measurement result map, connect the upper and lower cross Mark points, calculate the distance from any point on the edge contour to the connection line, and obtain the cutting accuracy value ; When there is no cross Mark point on the measurement result map or when there is only one cross Mark point, determine any target point on the edge profile, and identify the corresponding mark position of any target point on the edge profile on the measurement result map , calculating the distance from any target point on the edge contour to the corresponding mark position to obtain the cutting accuracy value; Wherein, the cutting accuracy detection result includes the cutting accuracy value. 9. The detection method of the liquid crystal panel according to claim 1 or 5, wherein the chamfering accuracy of the liquid crystal panel to be tested is measured according to the corner coordinate point and the edge profile to obtain the detection result of the chamfering accuracy, specifically Including the following steps: Using an adaptive threshold algorithm to obtain the chamfering feature flag in the region of interest of the measurement result image, and determine the chamfering detection area; Segmenting and extracting the chamfering detection area to obtain an image of the chamfering area; According to the preset chamfer area characteristic value, the preset chamfer width characteristic value and the preset chamfer height characteristic value, filter out the final chamfer image in the chamfer area image; determining the minimum circumscribed rectangle of the final chamfer according to the corner coordinate points and the edge profile; calculating a final chamfer width value and a final chamfer height value of the final chamfer according to the minimum circumscribed rectangle of the final chamfer; Wherein, the chamfering accuracy detection result includes the final chamfering width value and the final chamfering height value. 10. A detection system for a liquid crystal panel, characterized in that, the detection system is used for edge detection or/and defect detection of the liquid crystal panel; wherein, the edge detection system includes a data acquisition module for obtaining the The image of the measurement result of the LCD panel; A data processing module, configured to extract the region of interest of the measurement result image, and obtain corner coordinate points and/or edge contours in the measurement result image; an accuracy detection module, configured to measure the grinding accuracy of the liquid crystal panel to be tested according to the edge profile, and obtain a grinding accuracy detection result; and/or, used to measure the cutting accuracy of the liquid crystal panel to be tested according to the edge profile, Obtain a cutting accuracy detection result; and/or, measure the chamfering accuracy of the liquid crystal panel to be tested according to the corner coordinate point and the edge profile, and obtain a chamfering accuracy detection result; An output module, configured to output the testing results of the grinding accuracy and/or the testing results of the cutting accuracy and/or the testing results of the chamfering accuracy; The storage module is used for storing the grinding accuracy detection result and/or the cutting accuracy detection result and/or the chamfering accuracy detection result.

Images