CN116721039B - Image preprocessing method applied to automatic optical defect detection - Google Patents
Image preprocessing method applied to automatic optical defect detection Download PDFInfo
- Publication number
- CN116721039B CN116721039B CN202310989295.9A CN202310989295A CN116721039B CN 116721039 B CN116721039 B CN 116721039B CN 202310989295 A CN202310989295 A CN 202310989295A CN 116721039 B CN116721039 B CN 116721039B
- Authority
- CN
- China
- Prior art keywords
- image
- channel
- formula
- defect detection
- histogram
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 230000007547 defect Effects 0.000 title claims abstract description 46
- 238000001514 detection method Methods 0.000 title claims abstract description 31
- 238000007781 pre-processing Methods 0.000 title claims abstract description 16
- 230000003287 optical effect Effects 0.000 title claims abstract description 14
- 238000012937 correction Methods 0.000 claims abstract description 29
- 238000013507 mapping Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 23
- 238000005315 distribution function Methods 0.000 claims description 21
- 230000007246 mechanism Effects 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 238000012986 modification Methods 0.000 claims description 4
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000009825 accumulation Methods 0.000 claims 2
- 230000008569 process Effects 0.000 abstract description 19
- 239000003086 colorant Substances 0.000 abstract description 4
- 239000004973 liquid crystal related substance Substances 0.000 description 12
- 238000010586 diagram Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000007689 inspection Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 206010067484 Adverse reaction Diseases 0.000 description 1
- 230000006838 adverse reaction Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The application discloses an image preprocessing method applied to automatic optical defect detection, which relates to the technical field of image processing and comprises the steps of collecting an original image, inputting the original image, stretching a color channel, mapping a stretched RGB image to an HIS space and carrying out self-adaptive Gamma correction based on weighted histogram equalization. According to the Gamma self-adaptive correction method based on weighted histogram equalization, the contrast of the image can be enhanced on the premise of retaining the natural colors and abundant details of the original image in the pretreatment process of defect detection, and the problem that the contrast of the image cannot be enhanced on the premise of retaining the natural colors and abundant details of the original image in the pretreatment process of defect detection in the existing industrial detection is solved.
Description
Technical Field
The application relates to the technical field of image processing, in particular to an image preprocessing method applied to automatic optical defect detection.
Background
In the industrial inspection process, due to the influence of the manufacturing process of the target plate, the color of the substrate and the illumination environment, the acquired image samples have deviations of exposure or color in and among the plates, which are important factors affecting the inspection effect, so that the enhancement operation of the input image is necessary before the inspection method is executed, and the reduction of the color of the image and the increase of the contrast of the image are essential requirements for image enhancement. However, in the existing industrial detection, in the pretreatment process of defect detection, the contrast of an image cannot be enhanced on the premise of retaining the natural color and abundant details of an original image. For this purpose, the application provides an image preprocessing method applied to automated optical defect detection.
Disclosure of Invention
Aiming at the defects of the prior art, the application provides an image preprocessing method applied to automatic optical defect detection, and a Gamma self-adaptive correction method based on weighted histogram equalization, which can enhance the contrast of an image on the premise of keeping the natural color and rich details of an original image in the preprocessing process of defect detection.
In order to achieve the above purpose, the application is realized by the following technical scheme: an image preprocessing method applied to automatic optical defect detection, comprising the following steps:
step one, collecting an original image: acquiring a defect image by utilizing an automatic defect detection mechanism, acquiring a corresponding non-defect image through image registration, enabling the non-defect image to be aligned with the defect image, and taking the defect image as an original image;
step two, inputting an original image: the input width and the input height are respectivelyAnd->RGB original image of (2), the number of pixels in the image is +.>Each color channel is limited to between 0 and 255, and the input color image expression is:
;
in the method, in the process of the application,for pixel coordinates in each channel, +.>For inputting image coordinates>Pixel coordinates for the red channel,/>For green channel pixel coordinates +.>Pixel coordinates for blue channel, +.>;;
Step three, stretching the color channel: stretching each channel in the image within the stretching range of the maximum amplitude value tolerated by each channel;
mapping the stretched RGB image to an HIS space: only carrying out contrast enhancement processing on an I channel representing brightness, and retaining original information of an H channel and an S channel;
step five, self-adaptive Gamma correction based on weighted histogram equalization: the Gamma correction formula is used for carrying out self-adaptive correction on the weighted histogram equalization, and the expression is as follows:
;
wherein, the liquid crystal display device comprises a liquid crystal display device,is a Gamma correction value; />Is a rounding operation; />A brightness level for an input image; />A maximum brightness level for an input image; />Accumulating relevant parameters of a distribution function for brightness weighting in an original image;
step six, converting the image: and combining the I channel after the self-adaptive Gamma correction with other two channels in the HIS space, and then converting the I channel back to the RGB color space to acquire an enhanced image.
As a further aspect of the present application, in step one, the automated defect detection mechanism uses an area camera with a 25mm lens as an acquisition sensor, uses an AOI light source to provide illumination, moves the camera through a motion control card, captures images of different areas on the surface of the detected object, each captured image having a resolution of 1280×1024 and a real scene coverage of 42.7mm×34.1mm, repeatedly confirms the captured defect-free images by at least 5 workers, and sets them as template images for defect detection.
As a further aspect of the present application, in the third step, stretching each channel in the image, and pixels in the stretched red channel, green channel, and blue channel may be expressed as:
;
;
;
wherein:、/>maximum, minimum obtainable for all pixel positions in the red channel, respectively +.>、/>Maximum, minimum obtainable for all pixel positions in the green channel,/v>、/>Maximum value and maximum value obtainable for all pixel positions in blue channelSmall values.
In the fourth step, as a further scheme of the present application, a mapping formula for mapping the RGB image after the amplitude stretching into the HSI space is:
;
in the method, in the process of the application,for HSI space, +.>In order to map the function of the function,for RGB image +.>Is jointly represented by the following three formulas:
;
;
;
wherein:for the hue of the pixel location +.>For the color saturation of the pixel location, +.>For the brightness of the pixel location +.>Is a flute cardRed pixel position in the molar coordinate system, +.>Is the red pixel location in the cartesian coordinate system, and (2)>Is the red pixel location in the cartesian coordinate system, and (2)>Is the hue position in the conical space model.
As a further aspect of the present application, in step five,the formula of (2) is:
;
wherein, the liquid crystal display device comprises a liquid crystal display device,accumulating a distribution function for the luminance weights in the original function, < >>The relevant parameters of the distribution function are accumulated for the brightness weighting in the original image.
As a further aspect of the present application, in step five, the formula of the weighted cumulative distribution function of the brightness in the original image is calculated as:
;
in the method, in the process of the application,for the variables->Maximum value of>For weighted probability density function, +.>Is the sum of weighted probability density functions.
In the fifth step, a weighted histogram distribution function is further constructed to modify the statistical histogram, where the weighted histogram distribution function formula is:
;/>;
in the method, in the process of the application,、/>the minimum probability density function and the maximum probability density function after the histogram modification are respectively +.>As a probability density function>Is->For correction parameters +.>By using the clipped statistical histogram, the histogram clipping operation is used to control the level of contrast enhancement.
As a further aspect of the present application, in the weighted histogram distribution function formula, the correction parameters areBy using the statistical histogram after clipping to carry out adaptive setting, the correction parameter setting formula is as follows:
;
wherein, the liquid crystal display device comprises a liquid crystal display device,the formula of (2) is:
;
in the method, in the process of the application,is->And (5) a cut histogram.
As a further aspect of the application, inIn the formula of->The formula for performing histogram clipping is:
;
in the method, in the process of the application,for clipping limits, the clipping limits are taken as the mean value that occurs at each brightness level, and the clipping limits are formulated as:
。
the application has the beneficial effects that: the image preprocessing method applied to the automatic optical defect detection has the following beneficial effects: by adopting the Gamma self-adaptive correction method based on weighted histogram equalization, the contrast of the image can be enhanced and visual artifacts can be removed on the premise of keeping the natural colors and rich details of the original image in the preprocessing process of defect detection.
Drawings
FIG. 1 is a schematic diagram of an automated defect detection mechanism motion control card;
fig. 2 is a process contrast diagram for collecting too bright and too dark image samples, with the left side being a schematic diagram for processing too bright image samples and the right side being a schematic diagram for processing too dark image samples.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The application provides an image preprocessing method applied to automatic optical defect detection, which comprises the following steps:
step one, collecting an original image: acquiring a defect image by utilizing an automatic defect detection mechanism, acquiring a corresponding non-defect image through image registration, enabling the non-defect image to be aligned with the defect image, and taking the defect image as an original image;
step two, inputting an original image: the input width and the input height are respectivelyAnd->RGB original image of (2), the number of pixels in the image is +.>Each color channel is limited to between 0 and 255, and the input color image expression is:
;
in the method, in the process of the application,for pixel coordinates in each channel, +.>For inputting image coordinates>Pixel coordinates for the red channel,/>For green channel pixel coordinates +.>Pixel coordinates for blue channel, +.>;;
Step three, stretching the color channel: stretching each channel in the image within the stretching range of the maximum amplitude value tolerated by each channel;
mapping the stretched RGB image to an HIS space: only carrying out contrast enhancement processing on an I channel representing brightness, and retaining original information of an H channel and an S channel;
step five, self-adaptive Gamma correction based on weighted histogram equalization: the Gamma correction formula is used for carrying out self-adaptive correction on the weighted histogram equalization, and the expression is as follows:
;
wherein, the liquid crystal display device comprises a liquid crystal display device,is a Gamma correction value; />Is a rounding operation; />A brightness level for an input image; />A maximum brightness level for an input image; />Accumulating relevant parameters of a distribution function for brightness weighting in an original image;
step six, converting the image: and combining the I channel after the self-adaptive Gamma correction with other two channels in the HIS space, and then converting the I channel back to the RGB color space to acquire an enhanced image.
It should be noted that, since the human visual system is sensitive to the brightness intensity change, in the subsequent contrast enhancement operation, only the I channel representing the brightness is subjected to enhancement processing, and the original information of the H channel and the S channel is retained, because the information in the two channels does not directly affect the human perception of the image contrast.
As shown in fig. 1, in the first step, the automated defect detecting mechanism uses an area camera with a 25mm lens as an acquisition sensor, uses an AOI light source to provide illumination, moves the camera through a motion control card to capture images of different areas on the surface of the detected object, each captured image has a resolution of 1280×1024 and a real scene coverage of 42.7mm×34.1mm, and repeatedly confirms the captured defect-free images by at least 5 workers and sets them as template images for defect detection.
Specifically, in the third step, stretching each channel in the image, and the pixels in the stretched red channel, green channel, and blue channel may be expressed as:
;
;
;
wherein:、/>maximum, minimum obtainable for all pixel positions in the red channel, respectively +.>、/>Maximum, minimum obtainable for all pixel positions in the green channel,/v>、/>Maximum and minimum values available for all pixel positions in the blue channel; the stretched image is more informative in color and is also ready for subsequent contrast enhancement operations.
Further, in the fourth step, a mapping formula for mapping the RGB image after the amplitude stretching into the HSI space is:
;
in the method, in the process of the application,for HSI space, +.>In order to map the function of the function,for RGB image +.>Is jointly represented by the following three formulas:
;
;
;
wherein:for the hue of the pixel location +.>For the color saturation of the pixel location, +.>For the brightness of the pixel location +.>Is the red pixel location in the cartesian coordinate system, and (2)>Is the red pixel location in the cartesian coordinate system, and (2)>Is the red pixel location in the cartesian coordinate system, and (2)>Is the hue position in the conical space model.
In the fifth step, the first step is performed,the formula of (2) is:
;
wherein, the liquid crystal display device comprises a liquid crystal display device,accumulating a distribution function for the luminance weights in the original function, < >>The relevant parameters of the distribution function are accumulated for the brightness weighting in the original image.
Specifically, in step five, the formula of the weighted cumulative distribution function of the luminance in the original image is calculated as:
;
in the method, in the process of the application,for the variables->Maximum value of>For weighted probability density function, +.>Is the sum of weighted probability density functions.
Specifically, in the fifth step, a weighted histogram distribution function is further constructed to modify the statistical histogram to reduce the adverse reaction, where the weighted histogram distribution function formula is:
;/>;
in the method, in the process of the application,、/>the minimum probability density function and the maximum probability density function after the histogram modification are respectively +.>As a probability density function>Is->For correction parameters +.>By using the clipped statistical histogram, the histogram clipping operation is used to control the level of contrast enhancement.
It should be noted that, in the weighted histogram distribution function formula, the correction parametersBy using the statistical histogram after clipping to carry out adaptive setting, the correction parameter setting formula is as follows:
;
wherein, the liquid crystal display device comprises a liquid crystal display device,the formula of (2) is: />The method comprises the steps of carrying out a first treatment on the surface of the In (1) the->Is a cut histogram.
Further, inIn the formula of->The formula for performing histogram clipping is:
;
in the method, in the process of the application,for clipping limits, the clipping limits are taken as the mean value that occurs at each brightness level, and the clipping limits are formulated as:
。
according to the Gamma self-adaptive correction method based on weighted histogram equalization, the contrast of the image can be enhanced and visual artifacts can be removed on the premise of keeping natural colors and rich details of the original image in the pretreatment process of defect detection.
Examples. As shown in fig. 2, the sample of the too bright and too dark images is taken as the input test image, while the image enhanced by the method presented herein has better image quality, does not generate any visual artifacts, and the detected object in the image looks clearer and the color is brighter.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the application is not intended to limit the application, but to enable any modification, equivalent or improvement to be made without departing from the spirit and principles of the application.
Claims (9)
1. An image preprocessing method applied to automatic optical defect detection, which is characterized by comprising the following steps:
step one, collecting an original image: acquiring a defect image by utilizing an automatic defect detection mechanism, acquiring a corresponding non-defect image through image registration, enabling the non-defect image to be aligned with the defect image, and taking the defect image as an original image;
step two, inputting an original image: the method comprises the steps of inputting RGB original images with the width and the height of W and H respectively, wherein the number of pixels in the images is N=W×H, each color channel is limited between 0 and 255, and the input color image expression is:
I(w,h)={R(w,h),G(w,h),B(w,h)};
wherein, (w, h) is the pixel coordinates in each channel, I (w, h) is the input image coordinates, R (w, h) is the pixel coordinates of the red channel, G (w, h) is the pixel coordinates of the green channel, and B (w, h) is the pixel coordinates of the blue channel; w=1, …, W; h=1, …, H;
step three, stretching the color channel: stretching each channel in the image within the stretching range of the maximum amplitude value tolerated by each channel;
mapping the stretched RGB image to an HIS space: only carrying out contrast enhancement processing on an I channel representing brightness, and retaining original information of an H channel and an S channel;
step five, self-adaptive Gamma correction based on weighted histogram equalization: the Gamma correction formula is used for carrying out self-adaptive correction on the weighted histogram equalization, and the expression is as follows:
wherein T (I) is a Gamma correction value; round is a rounding operation; i is the brightness level of the input image; i max A maximum brightness level for an input image; gamma (l) is a relevant parameter of a brightness weighted accumulation distribution function in the original image;
step six, converting the image: and combining the I channel after the self-adaptive Gamma correction with other two channels in the HIS space, and then converting the I channel back to the RGB color space to acquire an enhanced image.
2. An image preprocessing method applied to automated optical defect detection according to claim 1, wherein in step one, an automated defect detection mechanism uses an area camera with a 25mm lens as an acquisition sensor, uses an AOI light source to provide illumination, moves the camera through a motion control card, captures images of different areas on the surface of the detected object, each captured image has a resolution of 1280×1024, a real scene coverage of 42.7mm×34.1mm, repeatedly confirms the captured defect-free images by at least 5 workers, and sets it as a template image for defect detection.
3. An image preprocessing method applied to automated optical defect detection according to claim 2, wherein in step three, stretching is performed on each channel in the image, and pixels in the stretched red channel, green channel and blue channel are expressed as:
wherein: max (R (w, h)), min (R (w, h)) are the maximum and minimum values that can be obtained for all pixel positions in the red channel, max (G (w, h)), min (G (w, h)) are the maximum and minimum values that can be obtained for all pixel positions in the green channel, and max (B (w, h)), min (B (w, h)) are the maximum and minimum values that can be obtained for all pixel positions in the blue channel, respectively.
4. The method for image preprocessing used in automated optical defect detection according to claim 1, wherein in step four, a mapping formula for mapping the RGB image subjected to the amplitude stretching into the HSI space is:
wherein [ H (w, H), S (w, H), I (w, H)]In the case of the HSI space,for mapping function, [ R (w, h), G (w, h), B (w, h)]For RGB image +.>Is jointly represented by the following three formulas:
wherein: h (w, H) is the hue of the pixel location, S (w, H) is the color saturation of the pixel location, I (w, H) is the brightness of the pixel location, R (x, y) is the red pixel location in the cartesian coordinate system, G (x, y) is the red pixel location in the cartesian coordinate system, B (x, y) is the red pixel location in the cartesian coordinate system, and θ (x, y) is the hue location in the conical space model.
5. The method of claim 1, wherein in step five, the formula of γ (l) is:
γ(l)=1-c w (l);
wherein c ω (l) And (3) accumulating the distribution function for the brightness weight in the original function, wherein gamma (l) is the related parameter of the distribution function for the brightness weight accumulation in the original image.
6. The method of claim 5, wherein in step five, the formula of the weighted cumulative distribution function of brightness in the original image is:
wherein, I max For the maximum value of the variable l, p w (l) Sigma p is a weighted probability density function w (l) Is the sum of weighted probability density functions.
7. The method of claim 6, wherein in step five, a weighted histogram distribution function is further constructed to modify the statistical histogram, and the weighted histogram distribution function formula is:
wherein p is max 、p min The minimum probability density function and the maximum probability density function after the histogram modification are respectively, p (l) is the probability density function, and alpha and c (l) are correction parameters.
8. The method of claim 7, wherein in the weighted histogram distribution function formula, the correction parameter α is adaptively set by using the clipped statistical histogram, and the correction parameter setting formula is:
wherein, the formula of p (l) is:
in the formula, h c (l) Is a cut histogram.
9. The method for image preprocessing used in automated optical defect detection according to claim 8, wherein in the formula of p (l), the formula of h (l) for histogram clipping is:
wherein h (l) is a histogram, T c For clipping limits, the clipping limits are taken as the mean value that occurs at each brightness level, and the clipping limits are formulated as:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310989295.9A CN116721039B (en) | 2023-08-08 | 2023-08-08 | Image preprocessing method applied to automatic optical defect detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310989295.9A CN116721039B (en) | 2023-08-08 | 2023-08-08 | Image preprocessing method applied to automatic optical defect detection |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116721039A CN116721039A (en) | 2023-09-08 |
CN116721039B true CN116721039B (en) | 2023-11-03 |
Family
ID=87873729
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310989295.9A Active CN116721039B (en) | 2023-08-08 | 2023-08-08 | Image preprocessing method applied to automatic optical defect detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116721039B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117495845B (en) * | 2023-12-25 | 2024-05-10 | 宁德时代新能源科技股份有限公司 | Blue gel detection method and device, electronic equipment and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109146826A (en) * | 2018-06-27 | 2019-01-04 | 华南理工大学 | A kind of image enchancing method and device |
CN109146811A (en) * | 2018-08-14 | 2019-01-04 | 长沙全度影像科技有限公司 | A kind of Adaptive contrast enhancement method of color image |
CN113989147A (en) * | 2021-10-26 | 2022-01-28 | 安徽大学 | Endoscope image enhancement method based on histogram equalization and improved unsharp mask |
CN114331896A (en) * | 2021-12-30 | 2022-04-12 | 安徽大学 | Image enhancement method and system based on image decomposition and spectral transformation |
CN116468636A (en) * | 2023-04-20 | 2023-07-21 | 无锡唐古半导体有限公司 | Low-illumination enhancement method, device, electronic equipment and readable storage medium |
-
2023
- 2023-08-08 CN CN202310989295.9A patent/CN116721039B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109146826A (en) * | 2018-06-27 | 2019-01-04 | 华南理工大学 | A kind of image enchancing method and device |
CN109146811A (en) * | 2018-08-14 | 2019-01-04 | 长沙全度影像科技有限公司 | A kind of Adaptive contrast enhancement method of color image |
CN113989147A (en) * | 2021-10-26 | 2022-01-28 | 安徽大学 | Endoscope image enhancement method based on histogram equalization and improved unsharp mask |
CN114331896A (en) * | 2021-12-30 | 2022-04-12 | 安徽大学 | Image enhancement method and system based on image decomposition and spectral transformation |
CN116468636A (en) * | 2023-04-20 | 2023-07-21 | 无锡唐古半导体有限公司 | Low-illumination enhancement method, device, electronic equipment and readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN116721039A (en) | 2023-09-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111563889B (en) | Liquid crystal screen Mura defect detection method based on computer vision | |
CN105100632B (en) | The method of adjustment and device of imaging device automatic exposure, imaging device | |
CN104063848B (en) | A kind of enhancement method of low-illumination image and device | |
CN101350933B (en) | Method for regulating lighteness of filmed display screen based on image inductor | |
CN104749184A (en) | Automatic optical detection method and automatic optical detection system | |
CN116721039B (en) | Image preprocessing method applied to automatic optical defect detection | |
CN101140365A (en) | Unevenness inspection method, method for manufacturing display panel, and unevenness inspection apparatus | |
CN103716547A (en) | Smart mode photographing method | |
CN107404647A (en) | Camera lens condition detection method and device | |
CN112583999B (en) | Method for detecting lens dirt of camera module | |
CN110163807B (en) | Low-illumination image enhancement method based on expected bright channel | |
CN108037142B (en) | Mask optical defect detection method based on image gray value | |
CN109801231B (en) | Image processing method of electrophoresis electronic paper detection equipment | |
CN112419261B (en) | Visual acquisition method and device with abnormal point removing function | |
CN104749801B (en) | High Precision Automatic optical detecting method and system | |
JP2009229197A (en) | Linear defect detecting method and device | |
CN116503324A (en) | Black glue module appearance detection method and system based on machine vision | |
CN109448012A (en) | A kind of method for detecting image edge and device | |
CN113450289B (en) | Method for automatically enhancing low illumination of face image in passenger traffic scene | |
CN112183158B (en) | Cereal type identification method of cereal cooking equipment and cereal cooking equipment | |
JP2004226272A (en) | Method and apparatus for detecting stain defect | |
CN109028234B (en) | Range hood capable of identifying smoke grade | |
JP4036048B2 (en) | Defect identification method | |
CN110706168A (en) | Image brightness adjusting method | |
JP3433333B2 (en) | Defect inspection method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |