WO2012129897A1 - 彩色图像去噪声的方法及其系统 - Google Patents
彩色图像去噪声的方法及其系统 Download PDFInfo
- Publication number
- WO2012129897A1 WO2012129897A1 PCT/CN2011/080040 CN2011080040W WO2012129897A1 WO 2012129897 A1 WO2012129897 A1 WO 2012129897A1 CN 2011080040 W CN2011080040 W CN 2011080040W WO 2012129897 A1 WO2012129897 A1 WO 2012129897A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- channel
- image
- information
- denoising
- cross
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000013501 data transformation Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims description 22
- 230000001629 suppression Effects 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 13
- 230000002146 bilateral effect Effects 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 4
- 241000023320 Luma <angiosperm> Species 0.000 claims description 3
- OSWPMRLSEDHDFF-UHFFFAOYSA-N methyl salicylate Chemical compound COC(=O)C1=CC=CC=C1O OSWPMRLSEDHDFF-UHFFFAOYSA-N 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 9
- 230000004927 fusion Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 6
- 230000006872 improvement Effects 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 229910044991 metal oxide Inorganic materials 0.000 description 2
- 150000004706 metal oxides Chemical class 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 229910052745 lead Inorganic materials 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
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
- G06T5/10—Image enhancement or restoration using non-spatial domain filtering
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Definitions
- the present invention relates to the field of video processing, and more particularly to color image denoising techniques.
- Video image denoising (noise reduction) is an important part of video processing. Since the image is inevitably affected by the interference of the transmission medium, the external and ambient optical signals, electrical signals, and mechanical damage during the recording, data compression, storage process, and transmission process, the video is made when the video image reaches the display terminal.
- the image content (the luminance value and the color value of each pixel) carried by the signal changes, and these changes are called image noise because of their spatial and temporal randomness.
- CMOS Complementary Metal-Oxide Semiconductor
- CCD Charge Coupled Device
- an embodiment of the present invention provides a method for denoising a color image, comprising the following steps:
- At least one chroma channel image is denoised according to the cross channel invariant information.
- Embodiments of the present invention also provide a color image denoising system, including:
- An image decomposition unit for decomposing a color image into a luminance channel image and N chrominance channel images, N ⁇ 2;
- a cross-channel invariant information extracting unit configured to extract cross-channel invariant information from the luminance channel image decomposed by the image decomposition unit;
- the denoising unit is configured to perform denoising processing on the at least one chroma channel image decomposed by the image decomposing unit according to the cross channel invariant information obtained by the cross channel invariant information extracting unit.
- the cross-channel invariant information is extracted from the luminance channel image for denoising processing of the chroma channel image, which can eliminate false color edges or textures, reduce blur at the edges, and obtain better overall denoising effect.
- the brightness channel image has information such as edge and texture. When using this information to denoise the chroma channel image, it can prevent the denoising strength from being different from other chrominances because the edge or texture in a certain chrominance channel image is not obvious. Causes false colored edges or textures, or blurry edges.
- N chroma channel images are denoised by using the channel invariant information, and the best denoising effect can be obtained.
- Gaussian smoothing is used to implement local data preprocessing, which requires less computational resources and is faster.
- the local data pre-processing is implemented by using a bilateral filter, and a better edge-preserving performance can be obtained, and the processing effect is better.
- FIG. 1 is a schematic flow chart of a method for denoising a color image according to a first embodiment of the present invention
- FIG. 2 is a schematic flow chart of extracting cross-channel invariant information from a luminance channel image in a method for denoising a color image according to a second embodiment of the present invention
- FIG. 3 is a schematic flow chart of extracting cross-channel invariant information from a luminance channel image in a method for denoising a color image according to a third embodiment of the present invention
- FIG. 4 is a schematic structural diagram of a system for color image denoising according to a fourth embodiment of the present invention.
- FIG. 5 is a schematic diagram showing an internal structure of a cross-channel invariant information extracting unit in a fifth embodiment of the present invention.
- FIG. 6 is a schematic diagram showing an internal structure of a noise removing unit in a fifth embodiment of the present invention.
- Fig. 7 is a schematic view showing an internal structure of a noise removing unit in a sixth embodiment of the present invention.
- a first embodiment of the invention relates to a method of denoising a color image.
- 1 is a flow chart showing a method of denoising the color image. The method includes the following steps:
- step 101 the color image is decomposed into a luminance channel image and N chrominance channel images, N ⁇ 2.
- the chrominance image is a single channel image of image data or a multi-channel joint image, such as a UV component in a YUV color space, or a Cb and Cr component in a YCbCr color space, or a YPbPr color space. Pb and Pr components, and so on.
- cross-channel invariant information is extracted from the luma channel image.
- the cross-channel invariant information can be any local image features such as edge information, texture information, noise strength, and the like. It can be understood that the cross-channel invariant information is not limited to edge information, texture information, noise intensity, but also image information shared between other channels (which is represented by edge information, texture information), or obtained by simple operation and stable. The information of each channel (which is represented by the noise intensity), and so on.
- step 103 the at least one chroma channel image is subjected to denoising processing according to the cross channel invariant information.
- the N chroma channel images obtained in step 101 are denoised according to the cross-channel invariant information to obtain an optimal denoising effect.
- the texture has a chromaticity bias
- the partial chrominance channel can be denoised only by using the cross-channel invariant information obtained from the luminance channel image.
- the cross-channel invariant information is extracted from the luminance channel image for denoising processing of the chroma channel image, which can eliminate false color edges or textures, reduce blur at the edges, and obtain better overall denoising effect.
- the brightness channel image has information such as edge and texture.
- this information can prevent the denoising strength from being different from other chrominances because the edge or texture in a certain chrominance channel image is not obvious. Causes false colored edges or textures, or blurry edges.
- a second embodiment of the invention relates to a method of denoising a color image.
- the second embodiment is improved on the basis of the first embodiment, and the main improvement is that an efficient cross-channel invariant information extraction method including preprocessing is employed in step 102.
- step 102 further includes the sub-steps shown in FIG. 2.
- step 201 local data pre-processing is performed on the partial image of the luminance channel image, which is used to suppress the influence of partial noise.
- the local data pre-processing may be Gaussian smoothing or filtering with a bilateral filter or the like. Using Gaussian smoothing to achieve local data preprocessing requires less computational resources and faster speeds.
- the use of bilateral filters for local data preprocessing can achieve better edge-preserving performance and better processing results. It can be understood that other types of filters can also be used for local data preprocessing according to specific application scenarios.
- step 202 local image feature information collection is performed.
- Local feature information collection includes collecting local texture intensity information, texture direction information, and the like.
- the edge texture extraction operator can be used to collect local feature information of the image, including but not limited to soble operator, laplace operator, canny operator and Gabor filter, etc. Depending on the application.
- the soble operator is used to collect local feature information of the image, and the absolute value of the response Sh of the soble operator in the horizontal direction of the local data region is taken as the extracted horizontal direction information Fh, and the soble operator is placed in The absolute value of the response Sv in the vertical direction of the local data region is taken as the extracted vertical direction information Fv.
- the information representing the local feature is calculated as the cross-channel invariant information.
- step 103 further includes the following sub-steps:
- the local block mean V0, the center line mean V1, and the center column mean V2 of the chroma channel image are calculated.
- Q can have many forms, which can be set according to the actual application environment.
- Q(Fh, Fv) k - Max(Fh, Fv). Where k is the factor used to control the degree of invariant information fusion across channels.
- a third embodiment of the present invention relates to a method of denoising a color image.
- the third embodiment is improved on the basis of the first embodiment.
- the main improvement is that after the local data transformation is performed on the luminance channel image, the cross-channel invariant information is extracted in the transform domain.
- This technical solution can utilize the different characteristics of the signal in the transform domain to extract the feature information such as the edge texture of the partial image data more effectively and accurately, so as to better utilize the information to denoise the chroma channel image. Specifically:
- Step 102 further includes the sub-steps shown in Figure 3:
- local data transformation is performed on the luminance channel image.
- Local data transformation is intended to transform the representation of image data, such as Fast Fourier Transform (Fast Fourier) Transform, referred to as "FFT", wavelet transform, and two-dimensional discrete cosine transform (Discrete Cosine) Transform, referred to as "DCT" for short.
- FFT Fast Fourier Transform
- DCT discrete cosine Transform
- the cross-channel invariant information extraction of the transform domain is to extract the edge texture characteristics of the local image data more efficiently and accurately by using the different characteristics of the signal in the transform domain.
- step 302 noise interference suppression is performed in the transform domain obtained by the local data transform.
- This step is mainly for performing noise suppression operations on coefficients in the local transform domain, with the aim of improving the reliability of local feature information extraction.
- the noise suppression method in the transform domain is a relatively mature technology and will not be described here.
- Feature information extraction is mainly the mining of the relationship between energy coefficients and image textures in the transform domain.
- the two-dimensional DCT transform is performed on the luminance channel image
- the horizontal direction edge information of the image can be extracted from the row of the coefficient matrix obtained after the transformation, such as the sum of the absolute values of the first row coefficients of the two-dimensional DCT coefficient matrix.
- Fv the vertical direction edge information of the image can be extracted from the column of the coefficient matrix obtained after the transformation, for example, the sum of the absolute values of the first column coefficient of the coefficient matrix is Fh
- the image of the coefficient matrix obtained after the transformation can extract the image
- the texture information such as the number of non-zero coefficients in the coefficient matrix, is F0.
- step 103 The local chrominance image denoising of step 103 can be performed in the same manner as step 103 of the second embodiment.
- the method embodiments of the present invention can all be implemented in software, hardware, firmware, and the like. Regardless of whether the invention is implemented in software, hardware, or firmware, the instruction code can be stored in any type of computer-accessible memory (eg, permanent or modifiable, volatile or non-volatile, solid state Or non-solid, fixed or replaceable media, etc.).
- the instruction code can be stored in any type of computer-accessible memory (eg, permanent or modifiable, volatile or non-volatile, solid state Or non-solid, fixed or replaceable media, etc.).
- the memory can be, for example, a programmable array logic (Programmable) Array Logic ("PAL” for short), Random Access Memory (“RAM”) Programmable Read Only Memory (“PROM”), read-only memory (Read-Only) Memory, referred to as "ROM”), electrically erasable programmable read-only memory (Electrically Erasable Programmable) ROM, referred to as "EEPROM”), magnetic disk, optical disk, Digital Versatile Disc (“DVD”) and so on.
- PAL programmable array logic
- RAM Random Access Memory
- PROM Programmable Read Only Memory
- ROM Read-Only Memory
- EEPROM electrically erasable programmable read-only memory
- magnetic disk magnetic disk
- optical disk optical disk
- DVD Digital Versatile Disc
- a fourth embodiment of the invention relates to a system for color image denoising.
- 4 is a schematic structural view of a system for denoising the color image.
- the color image denoising system includes:
- the cross-channel invariant information extracting unit is configured to extract cross-channel invariant information from the luminance channel image decomposed by the image decomposition unit.
- the cross-channel invariant information includes, but is not limited to, image information shared by the respective channels (such as edge texture information), and one or the other information of each channel information (such as noise intensity) that can be obtained by simple operation and stabilized. Several.
- the denoising unit is configured to perform denoising processing on the at least one chroma channel image decomposed by the image decomposing unit according to the cross channel invariant information obtained by the cross channel invariant information extracting unit.
- the denoising unit performs denoising processing on the N chroma channel images based on the cross channel invariant information.
- the color image is divided into two types of channel images, a luminance image and a chrominance image, and the cross-channel invariant information extracted from the luminance image is utilized in the chrominance image denoising process, and the color is guided.
- the degree image dynamically uses different denoising strategies to suppress noise.
- the first embodiment is a method embodiment corresponding to the present embodiment, and the present embodiment can be implemented in cooperation with the first embodiment.
- the related technical details mentioned in the first embodiment are still effective in the present embodiment, and are not described herein again in order to reduce repetition. Accordingly, the related art details mentioned in the present embodiment can also be applied to the first embodiment.
- a fifth embodiment of the present invention relates to a system for color image denoising.
- the fifth embodiment is improved on the basis of the fourth embodiment, and the main improvement is that an efficient cross-channel invariant information extraction method including preprocessing is employed in the cross-channel invariant information extracting unit.
- the cross-channel invariant information extracting unit includes the following modules:
- the pre-processing module is configured to perform local data pre-processing on the partial image of the luminance channel image, and the local data pre-processing is used to suppress the influence of partial noise.
- Local data of luminance image is preprocessed by local data to suppress the influence of partial noise and improve the accuracy of local feature information collection.
- the complexity of this processing depends on the accuracy requirements of feature information collection and extraction, such as low precision requirements, simple The Gaussian smoothing filter can be used. If the accuracy requirement is relatively high, it is not unreasonable to use a better-effect filter to implement pre-processing, such as bilateral filters.
- the collecting module is configured to collect local image feature information on the processing result of the preprocessing module.
- the collection module can collect local image feature information using a soble operator, a laplace operator, a canny operator, a Gabor filter, and the like.
- an extraction module configured to calculate, according to the local image feature information output by the collection module, information representing the local feature as cross-channel invariant information.
- the denoising unit may include the module shown in Figure 6:
- a local block mean calculation module for calculating a local block mean value V0 in the chroma channel image.
- the local block center line mean calculation module is used to calculate the local block center line mean value V1 in the chroma channel image.
- the local block center column mean value calculation module is used to calculate the local block center column mean value V2 in the chroma channel image.
- the cross-channel invariant information fusion denoising module is used for fusing the local data information of the chroma image and the invariant information between the channels, and comprehensively completing the denoising of the chroma image.
- the local block mean calculation module, the local block center line mean calculation module, and the partial block center column mean calculation module may also be disposed not in the denoising unit but in other units, and the change is only a conventional means.
- the second embodiment is a method embodiment corresponding to the present embodiment, and the present embodiment can be implemented in cooperation with the second embodiment.
- the related technical details mentioned in the second embodiment are still effective in the present embodiment, and are not described herein again in order to reduce repetition. Accordingly, the related art details mentioned in the present embodiment can also be applied to the second embodiment.
- a sixth embodiment of the present invention relates to a system for color image denoising.
- the sixth embodiment is improved on the basis of the fourth embodiment.
- the main improvement is that after the local data transformation is performed on the luminance channel image, the cross-channel invariant information is extracted in the transform domain.
- This technical solution can utilize the different characteristics of the signal in the transform domain to extract the feature information such as the edge texture of the partial image data more effectively and accurately, so as to better utilize the information to denoise the chroma channel image.
- the cross-channel invariant information extracting unit includes the following modules:
- a transform module for performing local data transformation on the luminance channel image.
- the noise interference suppression module is configured to perform noise interference suppression on the processing result of the transformation module.
- the noise interference suppression module is mainly for performing noise suppression operations on coefficients in the local transform domain, with the aim of improving the reliability of local feature information extraction.
- the noise suppression method in the transform domain is a relatively mature technology and will not be described here.
- an extraction module configured to extract feature information from the processing result of the noise interference suppression module as cross-channel invariant information.
- the third embodiment is a method embodiment corresponding to the present embodiment, and the present embodiment can be implemented in cooperation with the third embodiment.
- the related technical details mentioned in the third embodiment are still effective in the present embodiment, and are not described herein again in order to reduce repetition. Accordingly, the related art details mentioned in the present embodiment can also be applied to the third embodiment.
- cross-channel invariant information and some specific denoising methods are mentioned, which are only for ease of understanding and implementation, and are not necessarily limited to these specific forms and denoising modes, as long as cross-channels are utilized.
- the invariant information combined with the fusion and denoising of the local data information of the chroma image can achieve certain effects, and belongs to the scope of protection of the present invention.
- each unit or module mentioned in each system embodiment of the present invention is a logical unit or module.
- a logical unit or module may be a physical unit or module, or may be a A physical unit or a part of a module may also be implemented in a plurality of physical units or a combination of modules.
- the physical implementation of the units or modules themselves is not the most important, and the functions of the units or modules of the logic are implemented. Combination is the key to solving the technical problems raised by the present invention.
- the above various system embodiments of the present invention do not introduce a unit or module that is not closely related to solving the technical problem proposed by the present invention, which does not indicate that the above system implementation does not exist. Other units or modules.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
Description
Claims (15)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110081617.7A CN102156964B (zh) | 2011-03-31 | 2011-03-31 | 彩色图像去噪声的方法及其系统 |
CN201110081617.7 | 2011-03-31 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2012129897A1 true WO2012129897A1 (zh) | 2012-10-04 |
Family
ID=44438446
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2011/080040 WO2012129897A1 (zh) | 2011-03-31 | 2011-09-22 | 彩色图像去噪声的方法及其系统 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN102156964B (zh) |
WO (1) | WO2012129897A1 (zh) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103955903A (zh) * | 2014-05-09 | 2014-07-30 | 东南大学 | 一种权值窗口自适应非局部均值图像去噪方法 |
Families Citing this family (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102156964B (zh) * | 2011-03-31 | 2013-10-30 | 杭州海康威视数字技术股份有限公司 | 彩色图像去噪声的方法及其系统 |
CN102750671B (zh) * | 2011-09-28 | 2017-08-25 | 新奥特(北京)视频技术有限公司 | 一种图像彩色噪声去除方法 |
CN102497560B (zh) * | 2011-12-02 | 2014-04-02 | 浙江工商大学 | 一种去除复合视频解码图像色串的方法 |
CN103049756A (zh) * | 2012-11-16 | 2013-04-17 | 健雄职业技术学院 | 基于cema算法和纹理块匹配修复技术的自动提取与去除彩色图像内文字的方法 |
CN105447816B (zh) * | 2014-09-25 | 2019-01-08 | 杭州海康威视数字技术股份有限公司 | 一种多通道图像放大方法和装置 |
CN105631836B (zh) * | 2014-11-06 | 2018-10-23 | 杭州海康威视数字技术股份有限公司 | 一种图像降噪方法和装置 |
CN104749334A (zh) * | 2015-02-16 | 2015-07-01 | 燕山大学 | 基于模式识别的生物式异常水质评价系统设计方法 |
CN107480676B (zh) * | 2017-07-28 | 2019-12-24 | 浙江大华技术股份有限公司 | 一种车辆颜色识别方法、装置和电子设备 |
WO2019019772A1 (en) * | 2017-07-28 | 2019-01-31 | Zhejiang Dahua Technology Co., Ltd. | SYSTEMS AND METHODS FOR IMAGE PROCESSING |
CN107451976B (zh) * | 2017-07-28 | 2019-09-17 | 浙江大华技术股份有限公司 | 一种图像处理方法及装置 |
CN108810320B (zh) * | 2018-06-01 | 2020-11-24 | 深圳市商汤科技有限公司 | 图像质量提升方法和装置 |
CN110599406B (zh) | 2019-03-18 | 2022-05-03 | 上海立可芯半导体科技有限公司 | 一种图像增强方法及装置 |
CN113066033B (zh) * | 2021-04-19 | 2023-11-17 | 智领高新科技发展(北京)有限公司 | 一种彩色图像的多阶段去噪系统及方法 |
CN117376485B (zh) * | 2023-10-23 | 2024-04-23 | 上海为旌科技有限公司 | 一种yuv联合去除图像色度噪声的方法和滤波器 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101103374A (zh) * | 2005-01-11 | 2008-01-09 | 伊斯曼柯达公司 | 稀疏分布的彩色数字图像的噪声清除 |
CN101334836A (zh) * | 2008-07-30 | 2008-12-31 | 电子科技大学 | 一种融合色彩、尺寸和纹理特征的车牌定位方法 |
CN101562692A (zh) * | 2008-04-02 | 2009-10-21 | 英属开曼群岛商恒景科技股份有限公司 | 噪声降低装置及方法 |
CN102156964A (zh) * | 2011-03-31 | 2011-08-17 | 杭州海康威视软件有限公司 | 彩色图像去噪声的方法及其系统 |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1213592C (zh) * | 2001-07-31 | 2005-08-03 | 佳能株式会社 | 采用自适应二值化的图象处理方法和设备 |
CN100559836C (zh) * | 2007-09-20 | 2009-11-11 | 宝利微电子系统控股公司 | 一种数字图像降噪方法 |
CN101489034B (zh) * | 2008-12-19 | 2010-12-01 | 四川虹微技术有限公司 | 一种视频图像噪声估计与去除方法 |
CN101957984B (zh) * | 2010-08-30 | 2012-03-28 | 西安电子科技大学 | 基于非局部萎缩因子参数估计的图像去噪方法 |
CN101950414B (zh) * | 2010-09-02 | 2012-07-04 | 西安电子科技大学 | 自然图像非局部均值去噪方法 |
-
2011
- 2011-03-31 CN CN201110081617.7A patent/CN102156964B/zh active Active
- 2011-09-22 WO PCT/CN2011/080040 patent/WO2012129897A1/zh active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101103374A (zh) * | 2005-01-11 | 2008-01-09 | 伊斯曼柯达公司 | 稀疏分布的彩色数字图像的噪声清除 |
CN101562692A (zh) * | 2008-04-02 | 2009-10-21 | 英属开曼群岛商恒景科技股份有限公司 | 噪声降低装置及方法 |
CN101334836A (zh) * | 2008-07-30 | 2008-12-31 | 电子科技大学 | 一种融合色彩、尺寸和纹理特征的车牌定位方法 |
CN102156964A (zh) * | 2011-03-31 | 2011-08-17 | 杭州海康威视软件有限公司 | 彩色图像去噪声的方法及其系统 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103955903A (zh) * | 2014-05-09 | 2014-07-30 | 东南大学 | 一种权值窗口自适应非局部均值图像去噪方法 |
Also Published As
Publication number | Publication date |
---|---|
CN102156964B (zh) | 2013-10-30 |
CN102156964A (zh) | 2011-08-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2012129897A1 (zh) | 彩色图像去噪声的方法及其系统 | |
JP2004522372A (ja) | 時空間適応的雑音除去/高画質復元方法及びこれを応用した高画質映像入力装置 | |
Nithyananda et al. | Review on histogram equalization based image enhancement techniques | |
JP4290193B2 (ja) | 画像処理装置 | |
CN111161167B (zh) | 基于中通道补偿和自适应大气光估计的单幅图像去雾方法 | |
WO2000016265A1 (en) | A general image enhancement framework | |
US7526099B2 (en) | Motion picture data processing device, method, and program | |
JP2012018669A (ja) | デジタル入力画像を処理する方法 | |
CN101562692A (zh) | 噪声降低装置及方法 | |
CN111612705B (zh) | 一种增强ocr性能的背景图像消除方法 | |
KR100869134B1 (ko) | 이미지 처리장치 및 방법 | |
CN115578294B (zh) | 图像增强方法、装置、设备及存储介质 | |
KR102183518B1 (ko) | 이미지 신호로부터 계단 아티팩트들을 감소시키는 이미지 프로세싱 장치 | |
KR100839922B1 (ko) | 적응적 평균값 필터를 이용한 컬러 잡음 제거 장치 및 방법 | |
JP2004236185A (ja) | 信号処理装置および方法、記録媒体、並びにプログラム | |
JP5227906B2 (ja) | 映像記録システム | |
CN109167892B (zh) | 一种视频图像细节增强方法与系统 | |
CN113379629A (zh) | 卫星图像去噪方法、装置、计算机设备和存储介质 | |
Xiang et al. | Hazy image enhancement based on the full-saturation assumption | |
KR20140054733A (ko) | 영상 처리 방법 및 장치 | |
Mittal et al. | An efficient video enhancement method using LA* B* analysis | |
KR101022832B1 (ko) | Ccd센서의 스미어 열화 개선장치 및 방법 | |
Date et al. | Low light video enhancement: A Survey | |
Lu et al. | A multiresolution approach to recovering colors and details of clipped image regions | |
CN116977221A (zh) | 一种针对矿井重粉尘环境的图像复原方法 |
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: 11862288 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: 11862288 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 21.05.2014) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 11862288 Country of ref document: EP Kind code of ref document: A1 |