WO2020124873A1 - Procédé de traitement d'images - Google Patents

Procédé de traitement d'images Download PDF

Info

Publication number
WO2020124873A1
WO2020124873A1 PCT/CN2019/081610 CN2019081610W WO2020124873A1 WO 2020124873 A1 WO2020124873 A1 WO 2020124873A1 CN 2019081610 W CN2019081610 W CN 2019081610W WO 2020124873 A1 WO2020124873 A1 WO 2020124873A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
processed
pixels
area
value
Prior art date
Application number
PCT/CN2019/081610
Other languages
English (en)
Chinese (zh)
Inventor
陈云娜
金羽锋
Original Assignee
深圳市华星光电半导体显示技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳市华星光电半导体显示技术有限公司 filed Critical 深圳市华星光电半导体显示技术有限公司
Publication of WO2020124873A1 publication Critical patent/WO2020124873A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/20—Image enhancement or restoration using local operators
    • G06T5/30—Erosion or dilatation, e.g. thinning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/73—Deblurring; Sharpening
    • 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
    • G06T2207/20024—Filtering details
    • G06T2207/20028—Bilateral filtering

Definitions

  • the present invention relates to the field of display technology, and in particular to an image processing method.
  • Block-based discrete cosine transform (BDCT) coding has a wide range of applications in the field of compression.
  • Common image and video compression standards including JPEG and H264, use BDCT coding.
  • BDCT coding ignores the correlation of neighboring blocks, and a discontinuous phenomenon occurs at the boundary of the block, resulting in noise.
  • the image compressed by the BDCT encoding method will be subjected to noise reduction through global noise reduction, so as to eliminate the noise caused by the discontinuous boundary of the image block to improve The quality of the image.
  • a common method is to perform noise reduction on the image through bilateral filtering and noise reduction or use a sparse representation method of a pre-trained dictionary to perform noise reduction on the image.
  • the noise in the image is in different areas, and the human eye has different sensitivities. For relatively flat areas, the human eye is more sensitive to noise, and for textured areas, texture has a masking effect on noise. Not easy to detect.
  • the entire image adopts a uniform distance attenuation parameter and grayscale attenuation parameter, that is, a unified bilateral filtering formula is used to process the entire image.
  • An object of the present invention is to provide an image processing method, which can reduce the noise of the image while eliminating the blurring of the texture area caused by the noise reduction, and improve the display quality of the image.
  • the present invention first provides an image processing method, including the following steps:
  • Step S1 Provide the image to be processed
  • Step S2 dividing the image to be processed into a flat area, a texture area and an edge area;
  • Step S3. Use different bilateral filter functions to perform noise reduction processing on the flat area, the texture area and the edge area, thereby forming a processed image.
  • the image to be processed is a grayscale image; the image to be processed includes a plurality of pixels arranged in an array; each pixel has a corresponding original grayscale value;
  • the original gray value of each pixel of the image to be processed is also normalized to form a normalized gray value
  • the step S2 specifically includes:
  • Step S21 Calculate the gradient information of the image to be processed using the normalized gray values of multiple pixels, the gradient information includes gradient values corresponding to the multiple pixels; define pixels whose gradient values are less than the first threshold as flat pixels, Define pixels whose gradient value is greater than or equal to the first threshold value and less than or equal to the second threshold value as texture pixels, and define pixels whose gradient value is greater than or equal to the second threshold value as edge pixels; the first threshold value is less than the second threshold value;
  • Step S22 Divide the to-be-processed image into a plurality of blocks arranged in sequence, and calculate the number of flat pixels, texture pixels, and edge pixels in each block;
  • Step S23 Set one of the multiple blocks as the block to be analyzed. If the number of texture pixels in the block to be analyzed is greater than the number of flat pixels and greater than the number of edge pixels, the block to be analyzed Perform morphological expansion operations, otherwise keep the block to be analyzed unchanged;
  • Step S24 Repeat the above step S23 until multiple blocks have completed the operation of step S23;
  • Step S25 Divide the image to be processed in step S24 into a flat area, an edge area, and a texture area, where the gradient value of the pixels in the flat area is less than the first threshold, and the gradient value of the pixels in the texture area is greater than or equal to the first threshold Less than or equal to the second threshold, the gradient value of the pixels in the edge area is greater than the second threshold.
  • the step S3 is specifically: using a preset first bilateral filter function to convert the original gray value of each pixel in the flat area into a processing gray value, and using a preset second bilateral filter function to convert each pixel in the texture area The original gray value is converted into the processed gray value, and the preset third bilateral filter function is used to convert the original gray value of each pixel in the edge area into the processed gray value;
  • the first bilateral filter function is a
  • N(x) represents the area of a preset filter window in the image to be processed
  • y represents the position of a pixel in the filter window
  • x represents the position of the currently processed pixel
  • I(x) represents the currently processed pixel
  • the original gray value of, I(y) represents the original gray value of the pixel with y position
  • d1 is the preset first distance attenuation rate
  • r1 is the preset first gray attenuation rate
  • the second bilateral filter function is the first bilateral filter function
  • d2 is the preset second distance attenuation rate
  • r2 is the preset second gray attenuation rate
  • the third bilateral filter function is the third bilateral filter function
  • d3 is the preset third distance attenuation rate
  • r3 is the preset third gray attenuation rate
  • the first distance attenuation rate is greater than the second distance attenuation rate, and the second distance attenuation rate is greater than the third distance attenuation rate;
  • the first gray attenuation rate is greater than the second gray attenuation rate, and the second gray attenuation rate is greater than the third gray attenuation rate.
  • the image to be processed is obtained by extracting the luminance channel in the YCbCr data of the color image;
  • the image to be processed is an image after compression processing.
  • the normalized gray value of a plurality of pixels is used to calculate the gradient information of the image to be processed using an edge detection method.
  • the first threshold is 0.08, and the second threshold is 0.6.
  • the invention also provides an image processing method, including the following steps:
  • Step S1 Provide the image to be processed
  • Step S2 dividing the image to be processed into a flat area, a texture area and an edge area;
  • Step S3 Use different bilateral filter functions to perform noise reduction processing on the flat area, the texture area and the edge area to form a processed image
  • the image to be processed is a grayscale image; the image to be processed includes a plurality of pixels arranged in an array; each pixel has a corresponding original grayscale value;
  • the original gray value of each pixel of the image to be processed is also normalized to form a normalized gray value
  • the step S2 specifically includes:
  • Step S21 Calculate the gradient information of the image to be processed using the normalized gray values of multiple pixels, the gradient information includes gradient values corresponding to the multiple pixels; define pixels whose gradient values are less than the first threshold as flat pixels, Define pixels whose gradient value is greater than or equal to the first threshold value and less than or equal to the second threshold value as texture pixels, and define pixels whose gradient value is greater than or equal to the second threshold value as edge pixels; the first threshold value is less than the second threshold value;
  • Step S22 Divide the to-be-processed image into a plurality of blocks arranged in sequence, and calculate the number of flat pixels, texture pixels, and edge pixels in each block;
  • Step S23 Set one of the multiple blocks as the block to be analyzed. If the number of texture pixels in the block to be analyzed is greater than the number of flat pixels and greater than the number of edge pixels, the block to be analyzed Perform morphological expansion operations, otherwise keep the block to be analyzed unchanged;
  • Step S24 Repeat the above step S23 until multiple blocks have completed the operation of step S23;
  • Step S25 Divide the image to be processed in step S24 into a flat area, an edge area, and a texture area, where the gradient value of the pixels in the flat area is less than the first threshold, and the gradient value of the pixels in the texture area is greater than or equal to the first threshold Less than or equal to the second threshold, and the gradient value of the pixels in the edge area is greater than the second threshold;
  • the image to be processed is obtained by extracting the luminance channel in the YCbCr data of the color image;
  • the image to be processed is an image after compression processing.
  • the invention also provides an image processing method, including the following steps:
  • Step S1' providing an image to be processed
  • Step S2' dividing the image to be processed into a flat area and a texture area
  • Step S3' Perform sparse representation processing based on the pre-trained dictionary on the original gray value of each pixel in the flat area, and keep the original gray value of each pixel in the texture area unchanged, thereby forming a processed image.
  • the image to be processed is a grayscale image; the image to be processed includes a plurality of pixels arranged in an array; each pixel has a corresponding original grayscale value;
  • step S1' after the image to be processed is provided, the original gray value of each pixel of the image to be processed is also normalized to form a normalized gray value;
  • the step S2' specifically includes:
  • Step S21' using the normalized gray values of multiple pixels to calculate gradient information of the image to be processed, the gradient information including gradient values corresponding to the multiple pixels respectively; defining pixels whose gradient value is less than the first threshold as flat pixels , Define pixels whose gradient value is greater than or equal to the first threshold as texels;
  • Step S22' dividing the image to be processed into multiple blocks arranged in sequence, and calculating the number of flat pixels and texture pixels in each block;
  • Step S23' One of the multiple blocks is set as the block to be analyzed. If the number of texels in the block to be analyzed is greater than the number of flat pixels, it is determined that the block to be analyzed is a texture area. Otherwise, it is determined that the block to be analyzed is a flat area;
  • Step S24' Repeat the above step S23' until multiple blocks have completed the operation of step S23'.
  • the image to be processed is obtained by extracting the luminance channel in the YCbCr data of the color image;
  • the image to be processed is an image after compression processing.
  • the normalized gray value of a plurality of pixels is used to calculate the gradient information of the image to be processed using an edge detection method
  • the first threshold is 0.08.
  • the image to be processed is divided into flat regions, texture regions and edge regions, and different bilateral filter functions are used to perform noise reduction processing on the flat regions, texture regions and edge regions for
  • the distance attenuation rate and grayscale attenuation rate of the bilateral filter function for processing the flat area, the bilateral filter function for processing the texture area, and the bilateral filter function for processing the edge area are gradually reduced, thereby forming a processed image
  • the phenomenon of blurring the texture area caused by noise improves the display quality of the image.
  • FIG. 1 is a flowchart of a first embodiment of the image processing method of the present invention
  • step S2 is a flowchart of step S2 of the first embodiment of the image processing method of the present invention
  • FIG. 3 is a flowchart of a second embodiment of the image processing method of the present invention.
  • Fig. 4 is a flowchart of step S2' of the second embodiment of the image processing method of the present invention.
  • the first embodiment of the image processing method of the present invention includes the following steps:
  • Step S1 Provide an image to be processed.
  • the image to be processed is a grayscale image.
  • the image to be processed includes a plurality of pixels arranged in an array. Each pixel has a corresponding original gray value.
  • the image to be processed is obtained by extracting the luminance channel in the YCbCr data of the color image.
  • the image to be processed is an image that has undergone compression processing, for example, may be an image that has undergone compression processing using BDCT encoding.
  • step S1 after providing the image to be processed, the original gray value of each pixel of the image to be processed is also normalized to form a normalized gray value, and the normalized gray value of each pixel
  • the value range is 0-1.
  • Step S2 the image to be processed is divided into a flat area, a texture area and an edge area.
  • the step S2 specifically includes:
  • Step S21 Calculate gradient information of the image to be processed using the normalized gray values of multiple pixels, where the gradient information includes gradient values corresponding to the multiple pixels, respectively.
  • a pixel whose gradient value is less than the first threshold is defined as a flat pixel
  • a pixel whose gradient value is greater than or equal to the first threshold and less than or equal to the second threshold is defined as a texture pixel
  • a pixel whose gradient value is greater than or equal to the second threshold is defined as an edge pixel.
  • the first threshold is less than the second threshold.
  • the normalized gray value of a plurality of pixels is used to calculate the gradient information of the image to be processed by using an edge detection method such as a Sobel operator.
  • the range of the gradient value corresponding to each pixel is 0-1.
  • the first threshold is 0.08
  • the second threshold is 0.6.
  • Step S22 Divide the image to be processed into a plurality of blocks arranged in sequence, and calculate the number of flat pixels, texture pixels, and edge pixels in each block.
  • the method of dividing the image to be processed into blocks in step S22 may be selected according to actual needs, for example, it may be divided into multiple blocks arranged in 8 rows and 8 columns.
  • Step S23 Set one of the multiple blocks as the block to be analyzed. If the number of texture pixels in the block to be analyzed is greater than the number of flat pixels and greater than the number of edge pixels, the block to be analyzed Perform the morphological dilation operation, otherwise keep the block to be analyzed unchanged, thereby eliminating small holes in the texture and preventing additional noise from affecting the image quality.
  • Step S24 Repeat the above step S23 until multiple blocks have completed the operation of step S23.
  • Step S25 Divide the image to be processed in step S24 into a flat area, an edge area, and a texture area, where the gradient value of the pixels in the flat area is less than the first threshold, and the gradient value of the pixels in the texture area is greater than or equal to the first threshold Less than or equal to the second threshold, the gradient value of the pixels in the edge area is greater than the second threshold.
  • Step S3. Use different bilateral filter functions to perform noise reduction processing on the flat area, the texture area and the edge area, thereby forming a processed image.
  • the step S3 is specifically: using a preset first bilateral filter function to convert the original gray value of each pixel in the flat area into a processing gray value, and using a preset second bilateral filter function to convert the The original gray value of each pixel is converted into a processed gray value, and a preset third bilateral filter function is used to convert the original gray value of each pixel in the edge area into a processed gray value.
  • the first bilateral filter function is a
  • N(x) represents the area of a preset filter window in the image to be processed
  • y represents the position of a pixel in the filter window
  • x represents the position of the currently processed pixel
  • I(x) represents the currently processed pixel
  • the original gray value of, I(y) represents the original gray value of the pixel with y position
  • d1 is the preset first distance attenuation rate
  • r1 is the preset first gray attenuation rate.
  • the second bilateral filter function is the first bilateral filter function
  • d2 is the preset second distance attenuation rate
  • r2 is the preset second gray attenuation rate
  • the third bilateral filter function is the third bilateral filter function
  • d3 is the preset third distance attenuation rate
  • r3 is the preset third gray attenuation rate
  • the first distance attenuation rate is greater than the second distance attenuation rate, and the second distance attenuation rate is greater than the third distance attenuation rate.
  • the first gray attenuation rate is greater than the second gray attenuation rate, and the second gray attenuation rate is greater than the third gray attenuation rate.
  • the image to be processed is divided into flat regions, texture regions, and edge regions, and the flat regions, texture regions, and edge regions are reduced using different bilateral filter functions
  • Noise processing the distance attenuation rate and grayscale attenuation rate of the bilateral filter function for processing the flat area, the bilateral filter function for processing the texture area and the bilateral filter function for processing the edge area are gradually reduced
  • it can avoid the problem of using the same bilateral filter function to perform noise reduction on the entire image to blur the image in the texture area, and improve the display quality of the image.
  • the second embodiment of the image processing method of the present invention includes the following steps:
  • Step S1' providing an image to be processed.
  • the image to be processed is a grayscale image.
  • the image to be processed includes a plurality of pixels arranged in an array. Each pixel has a corresponding original gray value.
  • the image to be processed is obtained by extracting the luminance channel in the YCbCr data of the color image.
  • the image to be processed is an image that has undergone compression processing, for example, may be an image that has undergone compression processing using BDCT encoding.
  • the original gray value of each pixel of the image to be processed is also normalized to form a normalized gray value, and the normalized gray value of each pixel
  • the range of degrees is 0-1.
  • Step S2' the image to be processed is divided into a flat area and a texture area.
  • the step S2' specifically includes:
  • Step S21' Calculate the gradient information of the image to be processed using the normalized gray values of multiple pixels, where the gradient information includes gradient values corresponding to the multiple pixels, respectively.
  • Pixels with gradient values less than the first threshold are defined as flat pixels, and pixels with gradient values greater than or equal to the first threshold are defined as texture pixels.
  • the normalized gray value of a plurality of pixels is used to calculate the gradient information of the image to be processed using an edge detection method such as a Sobel operator.
  • the range of the gradient value corresponding to each pixel is 0-1.
  • the first threshold is 0.08.
  • step S22' the image to be processed is divided into a plurality of blocks arranged in sequence, and the number of flat pixels and texture pixels in each block is calculated.
  • step S22' the size of the divided block of the image to be processed is selected according to the size of the sparse representation processing window when the sparse representation processing is performed subsequently.
  • Step S23' One of the multiple blocks is set as the block to be analyzed. If the number of texels in the block to be analyzed is greater than the number of flat pixels, it is determined that the block to be analyzed is a texture area. Otherwise, it is determined that the block to be analyzed is a flat area.
  • Step S24' Repeat the above step S23' until multiple blocks have completed the operation of step S23'.
  • Step S3' Perform sparse representation processing based on the pre-trained dictionary on the original gray value of each pixel of the flat area, and keep the original gray value of each pixel of the texture area unchanged, thereby forming a processed image.
  • step S3' the original gray value of each pixel in the flat area is subjected to sparse representation processing based on a pre-trained dictionary to obtain multiple sets of calculation results corresponding to each pixel in the flat area, and calculating each group The result is averaged to obtain the processed gray value corresponding to each pixel of the flat area.
  • the image to be processed is divided into a flat area and an edge area, and the flat area is subjected to sparse representation processing based on a pre-trained dictionary and the texture area is kept unchanged, thereby Forming a processed image can ensure that the image has a good noise reduction effect, while avoiding the problem of blurring the image in the texture area due to the sparse representation processing of the texture area, and improving the display quality of the image.
  • the image to be processed is divided into a flat area, a texture area and an edge area, and different bilateral filter functions are used to perform noise reduction processing on the flat area, the texture area and the edge area.
  • the distance decay rate and gray decay rate of the bilateral filter function for processing the flat area, the bilateral filter function for processing the texture area, and the bilateral filter function for processing the edge area gradually decrease, thereby forming a processed image,
  • divide the image to be processed into a flat area and an edge area perform sparse representation processing based on the pre-trained dictionary on the flat area and keep the texture area unchanged, thereby forming a processed image, which can eliminate noise due to noise reduction while reducing the image.
  • the resulting blurring of texture areas improves the display quality of the image.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)
  • Facsimile Image Signal Circuits (AREA)

Abstract

La présente invention concerne un procédé de traitement d'images. Selon le procédé de traitement d'image objet de la présente invention, une image à traiter est divisée en une zone plate, une zone de texture et une zone de bord, un traitement de réduction de bruit est effectué sur la zone plate, la zone de texture et la zone de bord au moyen de différentes fonctions de filtrage bilatéral, et les taux d'atténuation de distance et les taux d'atténuation de niveau de gris de la fonction de filtrage bilatéral pour traiter la zone plate, de la fonction de filtrage bilatéral pour traiter la zone de texture et de la fonction de filtrage bilatéral pour traiter la zone de bord diminuent progressivement, de sorte qu'on obtient une image traitée ; ou bien l'image à traiter est divisée en une zone plate et une zone de bord, un traitement de représentation clairsemé sur la base d'un dictionnaire pré-entraîné est effectué sur la zone plate, et la zone de texture reste inchangée, de sorte qu'on obtient une image traitée. Le phénomène de flou de la zone de texture engendré par une réduction de bruit peut être éliminé tout en réalisant une réduction de bruit sur l'image, et la qualité d'affichage de l'image est améliorée.
PCT/CN2019/081610 2018-12-19 2019-04-04 Procédé de traitement d'images WO2020124873A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811558267.7A CN109584185B (zh) 2018-12-19 2018-12-19 图像处理方法
CN201811558267.7 2018-12-19

Publications (1)

Publication Number Publication Date
WO2020124873A1 true WO2020124873A1 (fr) 2020-06-25

Family

ID=65930142

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/081610 WO2020124873A1 (fr) 2018-12-19 2019-04-04 Procédé de traitement d'images

Country Status (2)

Country Link
CN (1) CN109584185B (fr)
WO (1) WO2020124873A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117686096A (zh) * 2024-01-30 2024-03-12 大连云智信科技发展有限公司 一种基于目标检测的畜禽动物体温检测方法
CN118037734A (zh) * 2024-04-12 2024-05-14 济宁丰玺生物材料有限公司 一种全降解塑料制品质量检测方法

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111986095B (zh) * 2019-05-22 2024-03-19 上海哔哩哔哩科技有限公司 基于边缘提取的图像处理方法及图像处理装置
CN113450264A (zh) * 2020-03-27 2021-09-28 上海途擎微电子有限公司 去振铃效应的方法及其相关装置
CN111429383B (zh) * 2020-04-13 2022-09-27 展讯通信（上海）有限公司 图像降噪方法及装置、计算机可读存储介质
CN113628119B (zh) * 2020-05-06 2024-05-03 北京君正集成电路股份有限公司 一种图像去噪过程中识别待去噪块的方法
CN112365413A (zh) * 2020-10-30 2021-02-12 湖北锐世数字医学影像科技有限公司 图像处理方法、装置、设备、***及计算机可读存储介质
CN113256534B (zh) * 2021-06-16 2022-01-07 湖南兴芯微电子科技有限公司 一种图像增强方法、装置及介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103116875A (zh) * 2013-02-05 2013-05-22 浙江大学 自适应双边滤波图像去噪方法
CN104680485A (zh) * 2013-11-27 2015-06-03 展讯通信（上海）有限公司 一种基于多分辨率的图像去噪方法及装置
CN107358586A (zh) * 2017-07-06 2017-11-17 中山大学 一种图像增强方法、装置及设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7599569B2 (en) * 2006-01-13 2009-10-06 Ati Technologies, Ulc Method and apparatus for bilateral high pass filter
TW200828983A (en) * 2006-12-27 2008-07-01 Altek Corp Method of eliminating image noise
CN106991652A (zh) * 2017-03-03 2017-07-28 杭州电子科技大学 稀疏度约束和字典原子大小自适应的彩色图像修复方法
CN108335264B (zh) * 2018-01-30 2021-08-03 武汉大学 一种基于混合分辨率稀疏字典学习的图像超分辨率方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103116875A (zh) * 2013-02-05 2013-05-22 浙江大学 自适应双边滤波图像去噪方法
CN104680485A (zh) * 2013-11-27 2015-06-03 展讯通信（上海）有限公司 一种基于多分辨率的图像去噪方法及装置
CN107358586A (zh) * 2017-07-06 2017-11-17 中山大学 一种图像增强方法、装置及设备

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117686096A (zh) * 2024-01-30 2024-03-12 大连云智信科技发展有限公司 一种基于目标检测的畜禽动物体温检测方法
CN117686096B (zh) * 2024-01-30 2024-04-16 大连云智信科技发展有限公司 一种基于目标检测的畜禽动物体温检测方法
CN118037734A (zh) * 2024-04-12 2024-05-14 济宁丰玺生物材料有限公司 一种全降解塑料制品质量检测方法

Also Published As

Publication number Publication date
CN109584185B (zh) 2020-10-16
CN109584185A (zh) 2019-04-05

Similar Documents

Publication Publication Date Title
WO2020124873A1 (fr) Procédé de traitement d'images
US11127122B2 (en) Image enhancement method and system
Lee et al. Contrast enhancement based on layered difference representation of 2D histograms
Wang et al. A fast single-image dehazing method based on a physical model and gray projection
US9196024B2 (en) Method and apparatus for enhancing color
CN109325922B (zh) 一种图像自适应增强方法、装置及图像处理设备
WO2016206087A1 (fr) Procédé et dispositif de traitement d'images à faible éclairage
US20200058102A1 (en) Background suppression method and detecting device in automatic optical detection of display panel
US10650500B2 (en) Image local contrast enhancement method
CN109919859B (zh) 一种户外场景图像去雾增强方法、计算设备及其存储介质
WO2021114564A1 (fr) Procédé d'amélioration d'image infrarouge à faible contraste
CN111612741B (zh) 一种基于失真识别的精确无参考图像质量评价方法
CN108280836B (zh) 一种图像处理方法及装置
CN109255752B (zh) 图像自适应压缩方法、装置、终端及存储介质
WO2022143421A1 (fr) Procédé et appareil d'estimation d'intensité de bruit, et dispositif électronique
WO2016008259A1 (fr) Procédé pour acquérir un histogramme, procédé pour régler de manière dynamique la luminosité et dispositif de traitement d'image
CN107292834B (zh) 红外图像细节增强方法
Mu et al. Low and non-uniform illumination color image enhancement using weighted guided image filtering
Nevriyanto et al. Image enhancement using the image sharpening, contrast enhancement, and Standard Median Filter (Noise Removal) with pixel-based and human visual system-based measurements
WO2021128498A1 (fr) Appareil et procédé de réduction de bruit adaptatif d'image
CN115393216A (zh) 基于偏振特性与大气传输模型的图像去雾方法和装置
CN109064413B (zh) 图像对比度增强方法及采用其的图像采集医疗设备
Ding et al. Color image enhancement with a human visual system based adaptive filter
CN112825189B (zh) 一种图像去雾方法及相关设备
CN109636749B (zh) 图像处理方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19897776

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19897776

Country of ref document: EP

Kind code of ref document: A1