CN117760560A - Method for detecting surface chromatic aberration of planar product based on chromatic data matrix - Google Patents
Method for detecting surface chromatic aberration of planar product based on chromatic data matrix Download PDFInfo
- Publication number
- CN117760560A CN117760560A CN202311606167.8A CN202311606167A CN117760560A CN 117760560 A CN117760560 A CN 117760560A CN 202311606167 A CN202311606167 A CN 202311606167A CN 117760560 A CN117760560 A CN 117760560A
- Authority
- CN
- China
- Prior art keywords
- data matrix
- matrix
- chromatic
- color difference
- product based
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000011159 matrix material Substances 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000004075 alteration Effects 0.000 title claims abstract description 14
- 238000001514 detection method Methods 0.000 claims abstract description 36
- 238000003708 edge detection Methods 0.000 claims description 10
- 230000000877 morphologic effect Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 239000003086 colorant Substances 0.000 claims description 4
- 238000011282 treatment Methods 0.000 claims description 4
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 238000003709 image segmentation Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000002950 deficient Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000001351 cycling effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Abstract
The invention discloses a method for detecting the surface chromatic aberration of a planar product based on a chromatic data matrix, which comprises the following steps: placing the object to be measured in a uniform white light box; scanning an object to be detected with high precision by using a high-resolution camera; uniformly dividing a shot image into a plurality of detection areas; calculating RGB color values of each region, and comparing the RGB color values with reference values to obtain color difference data; selecting weight parameters according to actual application scenes; calculating a chromaticity data matrix by using the color difference data and the weight parameters, and comparing the chromaticity data matrix with a standard matrix; and judging whether the color difference of each area and the whole area is within an acceptance range according to a preset standard.
Description
[ field of technology ]
The invention relates to the field of detection, in particular to a color difference detection technology for the surface of a planar product.
[ background Art ]
The appearance of planar products, such as tablet computers, is becoming more and more appreciated by users. Especially when high-end markets are involved, consumers have very high demands on the color consistency and perfection of the products.
The traditional color difference detection method often depends on human eyes to observe, and the method has the defects of strong subjectivity and easiness in being influenced by detection environments and human vision differences. In addition, with the automation of the production line and the increase of the product yield, the efficiency of the color difference detection mode depending on manpower is low, and the expansion is not easy.
[ invention ]
The invention aims to provide a plane product surface color difference detection method based on a chromaticity data matrix, which combines modern image processing technology and color science principles to provide a rapid, accurate and automatic color difference detection scheme.
In order to achieve the above object, the method for detecting the surface chromatic aberration of a planar product based on a chromatic data matrix according to the present invention comprises the following steps:
placing the object to be measured in a uniform white light box;
scanning an object to be detected with high precision by using a high-resolution camera;
uniformly dividing a shot image into a plurality of detection areas;
calculating RGB color values of each region, and comparing the RGB color values with reference values to obtain color difference data;
selecting weight parameters according to actual application scenes;
calculating a chromaticity data matrix by using the color difference data and the weight parameters, and comparing the chromaticity data matrix with a standard matrix;
and judging whether the color difference of each area and the whole area is within an acceptance range according to a preset standard.
According to the main features, when the photographed image is uniformly divided into a plurality of detection areas, the number of pixels of each area is required to be equal, and the edge detection method and the morphological processing method are adopted to ensure the clear boundary of the areas.
According to the main characteristic, the edge detection method is Canny, and the morphological treatment method comprises expansion and corrosion.
According to the above main feature, the step of removing noise in the image by a filtering technique is further included before uniformly dividing the photographed image into a plurality of detection areas.
According to the main characteristics, the color difference data and the weight parameters are utilized to calculate a chromaticity data matrix, and in comparison with a standard matrix, standard deviation calculation is carried out on data in the chromaticity data matrix and the standard matrix formed by R, G, B values of standard product colors produced in the same day.
According to the main characteristics, the method further comprises the steps of outputting a detection report, marking out unqualified areas and giving suggestions.
Compared with the prior art, the method disclosed by the invention has the following advantages: (1) the detection result is more accurate: based on advanced image processing technology and color science principle, more accurate color difference detection results can be provided; (2) automated operations may be implemented: the whole detection process can be fully automated, and the production efficiency is greatly improved; (3) the detection result has objectivity: the subjective judgment of people is not needed, and errors caused by human factors are reduced; (4) scalability: the detection parameters and standards can be adjusted according to different application scenes and requirements.
[ description of the drawings ]
Fig. 1 is a flow chart of a method for detecting surface color difference of a planar product based on a chromaticity data matrix for implementing the invention.
[ detailed description ] of the invention
Fig. 1 is a schematic flow chart of a method for detecting chromatic aberration of a planar product surface based on a chromatic data matrix according to the present invention. The method for detecting the surface chromatic aberration of the planar product based on the chromatic data matrix comprises the following steps:
step one: placing the object to be measured in a uniform white light box; in the implementation, the inside of the white light box adopts a multidirectional reflection design to ensure uniform scattering of light so as to eliminate shadows at corners and edges, and the light source is an LED light source with a height of CRI (Color Rendering Index) so as to ensure the authenticity and consistency of the color.
Step two: scanning an object to be detected with high precision by using a high-resolution camera; to ensure definition and detail capture of the image, the camera selection should have a resolution of at least 2000 ten thousand pixels, with a high performance image sensor mounted. And, the lens should have good color correction and distortion control functions.
Step three: uniformly dividing a shot image into a plurality of detection areas;
step four: calculating RGB color values of each region, and comparing the RGB color values with reference values to obtain color difference data;
step five: selecting weight parameters according to actual application scenes; the color difference perception in a real environment can be better simulated by introducing the weight parameters in consideration of different sensitivity of different application scenes to colors. The weight parameter is a multiplier or addend with a value of 1-10, and is actually adjusted according to the site, such as 10, +3, etc.
Step six: calculating a chromaticity data matrix by utilizing the color difference data and the weight parameters, and comparing the chromaticity data matrix with a standard matrix; wherein the chromaticity data matrix is a data structure integrating R, G, B values and weights thereof, and can describe color information more accurately. Through the steps, a matrix containing R, G, B values corresponding to each detection area (such as 20) can be obtained, standard deviation calculation is carried out on the data in the data matrix and a standard matrix formed by R, G, B values of standard product colors produced in the same day, and whether the chromatic aberration exceeds a tolerance range set by a factory is judged.
Step seven: and judging whether the color difference of each area and the whole area is within an acceptance range according to a preset standard.
In step three, the image segmentation should ensure that the number of pixels in each region is equal to ensure the accuracy of detection. In addition, edge detection and morphological processing technology are adopted to ensure the clear boundary of the region. The method specifically comprises the following detailed steps:
step 3.1: the image is read. Specifically, the image processing library, such as OpenCV in Python, is used to read the image, and specifically, the following may be adopted:
import cv2
image＝cv2.imread("path_to_image.jpg",cv2.IMREAD_COLOR)；
step 3.2: image segmentation is performed. In this embodiment, the image is divided into a grid of 4x5, specifically, the width and the height of the whole image are obtained first;
height,width,channels＝image.shape；
then calculating the width and the height of each region;
block_width＝width//5
block_height＝height//4；
these dimensions are then used to cycle through the images, extracting an image of each region.
Step 3.3: and (5) edge detection. The use of edge detection prior to segmentation may help ensure that the region boundaries are more sharp, and common edge detection methods such as Canny may be used.
edges＝cv2.Canny(image,100,200)；
Step 3.4: morphological treatment; to further ensure the definition of the boundaries morphological operations such as expansion and corrosion treatments are used, in particular as follows:
kernel＝cv2.getStructuringElement(cv2.MORPH_RECT,(3,3))
dilated＝cv2.dilate(edges,kernel,iterations＝1)。
thus, by combining image segmentation and processing, a clear detection area can be obtained, specifically as follows:
for iin range(4):
for j in range(5):
block＝image[i*block_height:(i+1)*block_height,j*block_width:(j+1)*block_width]
block_edges＝dilated[i*block_height:(i+1)*block_height,j*block_width:(j+1)*block_width]；
in the above procedure, block is a detection region, and block_edges is the boundary of the region.
In the fourth step, an average R, G, B value of each region is calculated through an image analysis algorithm and compared with a preset reference value to obtain color difference data, and the method specifically comprises the following steps:
step 4.1: reading an image; specifically, the OpenCV library is used to read the image.
Step 4.2: image segmentation is carried out; assuming that the image should be segmented into a grid of 4x5, the width and height of the entire image are obtained, after which the width and height of each region are calculated.
Step 4.3: calculating RGB color values of each region; specifically, the average R, G, B value of each region is calculated by cycling through each region.
Step 4.4: comparison with reference values: for each region, comparing the average RGB value of the region with a preset reference value to calculate the color difference, wherein the preset reference value is designated by a customer or manually designated by a to-be-inspected object of which the color value is selected on site as a standard value.
Step 4.5, outputting a result: and outputting or storing the color difference data of each area.
In specific implementation, the method further comprises the steps of outputting a detection report, marking unqualified areas and giving suggestions, and according to the detection result, a detailed report can be automatically generated, wherein the detailed report comprises color difference data of each area, the unqualified areas (the unqualified areas are the unqualified areas when the color difference exceeds the tolerance range set by a factory) and the positions of the unqualified areas.
For a better understanding of the above method, the following description is provided in connection with specific implementation procedures, which include the following steps:
the first step: configuration equipment and tools specifically include:
and (3) configuring a white light box: the LED light source with high CRI is used, and a multidirectional reflection structure is arranged inside the LED light source to ensure uniform light distribution;
configuring a high resolution camera: it at least comprises 2000 ten thousand pixels, and is equipped with high-performance image sensor and high-quality lens;
configuring image processing software: the image processing software can perform image segmentation, color value calculation, edge detection and morphological processing.
And a second step of: after all the devices are configured, the white light box is calibrated first, so that the uniformity of light is ensured. Then placing the plane product to be detected in an optical box, shooting by using a high-resolution camera, collecting an image, and inputting the image into image processing software for processing.
And a third step of: image processing; firstly, removing noise in an image through a filtering technology, and improving the quality of the image, wherein a filtering algorithm comprises Gaussian filtering, median filtering and the like. Then image segmentation is carried out, an edge detection technology Prewitt operator can be used for segmenting the image into a plurality of (e.g. 20) independent areas, and each area is ensured to have equal pixel number, so that calculation errors are reduced; finally, color value calculation is performed, namely, an average value of R, G, B three channels is calculated in each divided area, and the values provide basic data for subsequent color difference calculation.
Fourth step: color difference analysis; firstly, introducing weight parameters, and respectively introducing the weight parameters to R, G, B values of each region according to the requirements of actual application scenes. For example, if the change in red is more sensitive than green or blue in a certain application scenario, the weight of the red channel may be set higher; the color data matrix is then calculated, i.e. the weighted R, G, B values are combined into the color data matrix. The matrix can comprehensively describe the color characteristics of the surface of the planar product; and finally, calculating the standard deviation, namely comparing the chromaticity data matrix of each region with a preset standard value, and rapidly identifying the region with the exceeding standard of the color deviation by the method.
Fifth step: judging and outputting; and judging whether each area is qualified or not according to a preset standard, such as a standard deviation threshold value or a chromatic aberration upper limit. For example, if the standard deviation exceeds 0.3% of the set value, the product is regarded as defective. And then automatically generating a detailed report according to the detection result, wherein the report comprises color difference data, standard deviation, unqualified area positions and improvement suggestions for defective products of each detection area.
In the specific implementation, the planar product can be a planar product such as a tablet personal computer and the like with high requirements on appearance color difference.
Compared with the traditional manual detection method, the method disclosed by the invention has the following advantages: (1) the detection result is more accurate: based on advanced image processing technology and color science principle, more accurate color difference detection results can be provided; (2) automated operations may be implemented: the whole detection process can be fully automated, and the production efficiency is greatly improved; (3) the detection result has objectivity: the subjective judgment of people is not needed, and errors caused by human factors are reduced; (4) scalability: the detection parameters and standards can be adjusted according to different application scenes and requirements, so that the method is suitable for the different application scenes.
It will be understood that equivalents and modifications will occur to those skilled in the art in light of the present invention and their spirit, and all such modifications and substitutions are intended to be included within the scope of the present invention as defined in the following claims.
Claims (6)
1. A method for detecting the surface chromatic aberration of a planar product based on a chromatic data matrix comprises the following steps:
placing the object to be measured in a uniform white light box;
scanning an object to be detected with high precision by using a high-resolution camera;
uniformly dividing a shot image into a plurality of detection areas;
calculating RGB color values of each region, and comparing the RGB color values with reference values to obtain color difference data;
selecting weight parameters according to actual application scenes;
calculating a chromaticity data matrix by using the color difference data and the weight parameters, and comparing the chromaticity data matrix with a standard matrix;
and judging whether the color difference of each area and the whole area is within an acceptance range according to a preset standard.
2. The method for detecting the surface chromatic aberration of a planar product based on a chromatic data matrix as claimed in claim 1, wherein: when the shot image is uniformly divided into a plurality of detection areas, the equal number of pixels of each area is ensured, and the edge detection method and the morphological processing method are adopted to ensure the clear boundary of the areas.
3. The method for detecting the surface chromatic aberration of a planar product based on a chromatic data matrix as claimed in claim 2, wherein: the edge detection method is Canny, and the morphological treatment method comprises expansion and corrosion.
4. The method for detecting the surface chromatic aberration of a planar product based on a chromatic data matrix as claimed in claim 1, wherein: the method further includes the step of removing noise from the image by a filtering technique before uniformly dividing the photographed image into a plurality of detection areas.
5. The method for detecting the surface chromatic aberration of a planar product based on a chromatic data matrix as claimed in claim 1, wherein: and calculating a chromaticity data matrix by using the color difference data and the weight parameters, and comparing the chromaticity data matrix with a standard matrix, wherein in the comparison, standard deviation calculation is carried out on the data in the chromaticity data matrix and the standard matrix formed by R, G, B values of standard product colors produced on the same day.
6. The method for detecting the surface chromatic aberration of a planar product based on a chromatic data matrix as claimed in claim 1, wherein: the method further comprises the steps of outputting a detection report, marking out unqualified areas and giving suggestions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311606167.8A CN117760560A (en) | 2023-11-28 | 2023-11-28 | Method for detecting surface chromatic aberration of planar product based on chromatic data matrix |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311606167.8A CN117760560A (en) | 2023-11-28 | 2023-11-28 | Method for detecting surface chromatic aberration of planar product based on chromatic data matrix |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117760560A true CN117760560A (en) | 2024-03-26 |
Family
ID=90320907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311606167.8A Pending CN117760560A (en) | 2023-11-28 | 2023-11-28 | Method for detecting surface chromatic aberration of planar product based on chromatic data matrix |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117760560A (en) |
-
2023
- 2023-11-28 CN CN202311606167.8A patent/CN117760560A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5647878B2 (en) | Steel pipe internal corrosion analysis apparatus and steel pipe internal corrosion analysis method | |
| CN105335963A (en) | Edge defect detection method and apparatus | |
| CN110110131B (en) | Airplane cable support identification and parameter acquisition method based on deep learning and binocular stereo vision | |
| CN116030060B (en) | Plastic particle quality detection method | |
| CN105096348B (en) | The device and method of tint plate in detection image | |
| CN115082451B (en) | Stainless steel soup ladle defect detection method based on image processing | |
| CN110490826B (en) | Fog drop sample image processing method in camera | |
| CN114299070B (en) | Method and related device for detecting mura defects of display screen | |
| CN112381751A (en) | Online intelligent detection system and method based on image processing algorithm | |
| CN109064439B (en) | Partition-based single-side light-entering type light guide plate shadow defect extraction method | |
| CN114119591A (en) | Display screen picture quality detection method | |
| CN104749801B (en) | High Precision Automatic optical detecting method and system | |
| CN111641822B (en) | Method for evaluating quality of repositioning stereo image | |
| CN114359412A (en) | Automatic calibration method and system for external parameters of camera facing to building digital twins | |
| CN112070762A (en) | Mura defect detection method and device for liquid crystal panel, storage medium and terminal | |
| CN112819017B (en) | High-precision color cast image identification method based on histogram | |
| CN117115610A (en) | Metal surface defect detection method and system based on multi-angle image exposure fusion | |
| CN115546141A (en) | Small sample Mini LED defect detection method and system based on multi-dimensional measurement | |
| CN117760560A (en) | Method for detecting surface chromatic aberration of planar product based on chromatic data matrix | |
| CN116681677A (en) | Lithium battery defect detection method, device and system | |
| CN110956640B (en) | Heterogeneous image edge point detection and registration method | |
| CN111260625B (en) | Automatic extraction method for offset printing large image detection area | |
| CN114820597A (en) | Smelting product defect detection method, device and system based on artificial intelligence | |
| CN212646436U (en) | Artificial board surface flaw detection device | |
| TW200842339A (en) | Mura detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |