CN117649661B - Carbon nanotube preparation state image processing method - Google Patents
Carbon nanotube preparation state image processing method Download PDFInfo
- Publication number
- CN117649661B CN117649661B CN202410128175.4A CN202410128175A CN117649661B CN 117649661 B CN117649661 B CN 117649661B CN 202410128175 A CN202410128175 A CN 202410128175A CN 117649661 B CN117649661 B CN 117649661B
- Authority
- CN
- China
- Prior art keywords
- image
- characteristic
- state
- feature
- representing
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/693—Acquisition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a carbon nanotube preparation state image processing method, which belongs to the technical field of image processing and comprises the following steps: s1, scanning the surface of a carbon nanotube sample by using a scanning electron microscope to obtain a surface image, and denoising the surface image to obtain a characteristic image; s2, determining state characteristic values of all pixel points in the characteristic image to obtain a state characteristic matrix of the characteristic image; s3, correcting the characteristic image according to the state characteristic matrix of the characteristic image to obtain a standard surface image, and finishing image processing. The method comprises the steps of carrying out denoising treatment on a surface image of a scanned carbon nanotube sample, extracting a state feature matrix representing pixel point features of the whole image, and obtaining the state feature matrix through convolution, feature calculation and the like; the invention also carries out color correction on the image according to the state characteristic matrix, ensures the definition of the carbon nanotube sample image, and further improves the accuracy of observation.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a carbon nanotube preparation state image processing method.
Background
The carbon nanotube is a nano-sized tubular structure formed by carbon atoms in a certain mode, has excellent physical properties such as high strength, high electrical conductivity, high thermal conductivity and the like, and can fully exert the advantages of the carbon nanotube and other materials by combining the carbon nanotube with the other materials, so that the performance of the materials is improved. The dispersion state of the carbon nanotubes is a key factor, and directly affects the bonding performance of the carbon nanotubes with other materials. The dispersion state of the carbon nanotubes is generally observed through an optical microscope, a scanning electron microscope, a transmission electron microscope and the like, so that the quality of the collected images of the carbon nanotubes directly determines the observation result, and how to improve the image definition is an urgent problem to be solved.
Disclosure of Invention
In order to solve the problems, the invention provides a method for processing a carbon nanotube preparation state image.
The technical scheme of the invention is as follows: the carbon nanotube preparation state image processing method comprises the following steps:
s1, scanning the surface of a carbon nanotube sample by using a scanning electron microscope to obtain a surface image, and denoising the surface image to obtain a characteristic image;
s2, determining state characteristic values of all pixel points in the characteristic image to obtain a state characteristic matrix of the characteristic image;
s3, correcting the characteristic image according to the state characteristic matrix of the characteristic image to obtain a standard surface image, and finishing image processing.
Scanning electron microscopy is a common characterization means that obtains surface topography and composition information of a sample by scanning the surface of the sample and by detecting secondary or reflected electron signals from the sample.
Further, S2 comprises the following sub-steps:
s21, determining color weights of all pixel points according to RGB components of all pixel points in the feature image;
s22, constructing a state characteristic model, inputting the color weight of each pixel point into the state characteristic model, and determining the state characteristic value of each pixel point;
s23, generating a state feature matrix of the feature image according to the state feature values of the pixel points.
Further, in S21, the color weight q of the pixel point in the ith row and the jth column in the feature image ij The calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein R is ij Representing the red component, G, of the ith row and jth column pixel points in the feature image ij Representing green component of ith row and jth column pixel points in characteristic image, B ij Representing blue component of pixel point in ith row and jth column in characteristic image, R 0 Representing the mean value of red components of all pixel points in the characteristic image, G 0 Representing the green component mean value of all pixel points in the characteristic image, B 0 Representing the mean of the blue components of all pixels in the feature image.
Further, the state feature model comprises a depth convolution module, a global feature module and an output module which are sequentially connected.
The beneficial effects of the above-mentioned further scheme are: in the invention, the depth convolution module comprises convolution kernels with the same number as the pixel points of the characteristic image, and each convolution kernel is used for extracting the edge characteristics of each pixel point in the characteristic image. The output module is used for comprehensively outputting the state characteristic values of the pixel points.
According to the method, red, green and blue components of each pixel point in the characteristic image are compared with the average value of the red, green and blue components of all the pixel points, and the color weight of each pixel point is determined; and inputting each pixel point and the color weight thereof into a state feature model, respectively extracting features of each pixel point by utilizing each convolution kernel of a depth convolution layer in the state feature model, calculating the output of each convolution kernel in the depth convolution module and the color weight value corresponding to each convolution kernel processing pixel point by utilizing a global feature module to obtain global features, calculating the RGB values of the global features and the processing pixels corresponding to each output layer by utilizing each output layer of an output module, and determining the state feature value of each pixel point.
Further, the expression of the global feature module is:wherein Q represents the output of the global feature module, C m Representing the output, K, of the mth convolution kernel in the depth convolution module m Represents the size, q, of the mth convolution kernel in the depth convolution module m Representing color weight corresponding to pixel point processed by mth convolution kernel in depth convolution module, B m The step length of the mth convolution kernel in the depth convolution module is represented, M represents the number of convolution kernels of the depth convolution module, sigma represents the standard deviation of all convolution kernel outputs, exp (·) represents an exponential function, and q represents the hyper-parameter of the global feature module.
Further, the expression of the output module is:wherein Z represents the output of the nth output layer in the output module, Q represents the output of the global feature module, R represents the red component of the pixel point corresponding to the nth output layer, G represents the green component of the pixel point corresponding to the nth output layer, B represents the blue component of the pixel point corresponding to the nth output layer, and ln (·) represents a logarithmic function.
Further, in S23, the specific method for generating the state feature matrix is as follows: the method comprises the steps of taking the number of rows of pixel points of a feature image as the number of rows of a state feature matrix, taking the number of columns of pixel points of the feature image as the number of columns of the state feature matrix, taking the state feature value of each row of pixel points as the element of each row of the state feature matrix, and generating the state feature matrix of the feature image.
Further, S3 comprises the following sub-steps:
s31, determining a red component correction coefficient, a green component correction coefficient and a blue component correction coefficient of each pixel point in the characteristic image according to the state characteristic matrix of the characteristic image;
s32, correcting the characteristic image according to the red component correction coefficient, the green component correction coefficient and the blue component correction coefficient of the characteristic image to obtain a standard surface image, and finishing image processing.
And taking the average value of the red component correction coefficient and the original red component value of each pixel point of the characteristic image as the latest red component value, blue component and green component of the corresponding pixel point in the standard surface image.
Further, in S31, the correction coefficient of the red component of the pixel point in the ith row and the jth column in the feature imageThe calculation formula of (2) is as follows: />The method comprises the steps of carrying out a first treatment on the surface of the Wherein lambda represents the eigenvalue of the state eigenvalue matrix, R ij Representing the red component of the ith row and jth column pixel points in the feature image,/and (ii)>Representing an upward rounding, P 0 Representing the position of the pixel point corresponding to the maximum value of the red component in the characteristic image, P ij Representing the position of the pixel point in the ith row and the jth column in the characteristic image, wherein dis (·) represents a Euclidean distance function;
in S31, the green component correction coefficient of the ith row and jth column pixel points in the feature imageThe calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein G is ij Representing green component, P of ith row and jth column pixel points in characteristic image 1 Representing the position of the pixel point corresponding to the maximum value of the green component;
in S31, the green component correction coefficient of the ith row and jth column pixel points in the feature imageThe calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein B is ij Representing blue component, P of pixel point in ith row and jth column in characteristic image 2 The position of the maximum value of the blue component corresponding to the pixel point is indicated.
The beneficial effects of the invention are as follows: the method comprises the steps of carrying out denoising treatment on a surface image of a scanned carbon nanotube sample, extracting a state feature matrix representing pixel point features of the whole image, and obtaining the state feature matrix through convolution, feature calculation and the like; the invention also carries out color correction on the image according to the state characteristic matrix, ensures the definition of the carbon nanotube sample image, and further improves the accuracy of observation.
Drawings
Fig. 1 is a flowchart of a method for processing a carbon nanotube preparation state image.
Detailed Description
Embodiments of the present invention are further described below with reference to the accompanying drawings.
As shown in fig. 1, the present invention provides a method for processing a carbon nanotube preparation status image, comprising the steps of:
s1, scanning the surface of a carbon nanotube sample by using a scanning electron microscope to obtain a surface image, and denoising the surface image to obtain a characteristic image;
s2, determining state characteristic values of all pixel points in the characteristic image to obtain a state characteristic matrix of the characteristic image;
s3, correcting the characteristic image according to the state characteristic matrix of the characteristic image to obtain a standard surface image, and finishing image processing.
Scanning electron microscopy is a common characterization means that obtains surface topography and composition information of a sample by scanning the surface of the sample and by detecting secondary or reflected electron signals from the sample.
In an embodiment of the present invention, S2 comprises the following sub-steps:
s21, determining color weights of all pixel points according to RGB components of all pixel points in the feature image;
s22, constructing a state characteristic model, inputting the color weight of each pixel point into the state characteristic model, and determining the state characteristic value of each pixel point;
s23, generating a state feature matrix of the feature image according to the state feature values of the pixel points.
In the embodiment of the invention, in S21, the color weight q of the pixel point in the ith row and the jth column in the feature image ij The calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein R is ij Representing the red component, G, of the ith row and jth column pixel points in the feature image ij Representing green component of ith row and jth column pixel points in characteristic image, B ij Representing blue component of pixel point in ith row and jth column in characteristic image, R 0 Representing the mean value of red components of all pixel points in the characteristic image, G 0 Representing the green component mean value of all pixel points in the characteristic image, B 0 Representing the mean of the blue components of all pixels in the feature image.
In the embodiment of the invention, the state characteristic model comprises a depth convolution module, a global characteristic module and an output module which are sequentially connected.
In the invention, the depth convolution module comprises convolution kernels with the same number as the pixel points of the characteristic image, and each convolution kernel is used for extracting the edge characteristics of each pixel point in the characteristic image. The output module is used for comprehensively outputting the state characteristic values of the pixel points.
According to the method, red, green and blue components of each pixel point in the characteristic image are compared with the average value of the red, green and blue components of all the pixel points, and the color weight of each pixel point is determined; and inputting each pixel point and the color weight thereof into a state feature model, respectively extracting features of each pixel point by utilizing each convolution kernel of a depth convolution layer in the state feature model, calculating the output of each convolution kernel in the depth convolution module and the color weight value corresponding to each convolution kernel processing pixel point by utilizing a global feature module to obtain global features, calculating the RGB values of the global features and the processing pixels corresponding to each output layer by utilizing each output layer of an output module, and determining the state feature value of each pixel point.
In the embodiment of the invention, the expression of the global feature module is as follows:wherein Q represents the output of the global feature module, C m Representing the output, K, of the mth convolution kernel in the depth convolution module m Represents the size, q, of the mth convolution kernel in the depth convolution module m Representing color weight corresponding to pixel point processed by mth convolution kernel in depth convolution module, B m The step length of the mth convolution kernel in the depth convolution module is represented, M represents the number of convolution kernels of the depth convolution module, sigma represents the standard deviation of all convolution kernel outputs, exp (·) represents an exponential function, and q represents the hyper-parameter of the global feature module.
In the embodiment of the invention, the expression of the output module is:wherein Z represents the output of the nth output layer in the output module, Q represents the output of the global feature module, R represents the red component of the pixel point corresponding to the nth output layer, G represents the green component of the pixel point corresponding to the nth output layer, B represents the blue component of the pixel point corresponding to the nth output layer, and ln (·) represents a logarithmic function.
In the embodiment of the present invention, in S23, a specific method for generating the state feature matrix is as follows: the method comprises the steps of taking the number of rows of pixel points of a feature image as the number of rows of a state feature matrix, taking the number of columns of pixel points of the feature image as the number of columns of the state feature matrix, taking the state feature value of each row of pixel points as the element of each row of the state feature matrix, and generating the state feature matrix of the feature image.
In an embodiment of the present invention, S3 comprises the following sub-steps:
s31, determining a red component correction coefficient, a green component correction coefficient and a blue component correction coefficient of each pixel point in the characteristic image according to the state characteristic matrix of the characteristic image;
s32, correcting the characteristic image according to the red component correction coefficient, the green component correction coefficient and the blue component correction coefficient of the characteristic image to obtain a standard surface image, and finishing image processing.
And taking the average value of the red component correction coefficient and the original red component value of each pixel point of the characteristic image as the latest red component value, blue component and green component of the corresponding pixel point in the standard surface image.
In the embodiment of the present invention, in S31, the correction coefficient of the red component of the pixel point in the ith row and the jth column in the feature imageThe calculation formula of (2) is as follows: />The method comprises the steps of carrying out a first treatment on the surface of the Wherein lambda represents the eigenvalue of the state eigenvalue matrix, R ij Representing the red component of the ith row and jth column pixel points in the feature image,/and (ii)>Representing an upward rounding, P 0 Representing the position of the pixel point corresponding to the maximum value of the red component in the characteristic image, P ij Representing the position of the pixel point in the ith row and the jth column in the characteristic image, wherein dis (·) represents a Euclidean distance function;
in S31, the green component correction coefficient of the ith row and jth column pixel points in the feature imageThe calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein G is ij Representing green component, P of ith row and jth column pixel points in characteristic image 1 Representing the position of the pixel point corresponding to the maximum value of the green component;
in S31, the green component of the ith row and jth column pixels in the feature image is correctedCoefficients ofThe calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein B is ij Representing blue component, P of pixel point in ith row and jth column in characteristic image 2 The position of the maximum value of the blue component corresponding to the pixel point is indicated.
Those of ordinary skill in the art will recognize that the embodiments described herein are for the purpose of aiding the reader in understanding the principles of the present invention and should be understood that the scope of the invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific modifications and combinations from the teachings of the present disclosure without departing from the spirit thereof, and such modifications and combinations remain within the scope of the present disclosure.
Claims (4)
1. A method for processing a state image of a carbon nanotube preparation, comprising the steps of:
s1, scanning the surface of a carbon nanotube sample by using a scanning electron microscope to obtain a surface image, and denoising the surface image to obtain a characteristic image;
s2, determining state characteristic values of all pixel points in the characteristic image to obtain a state characteristic matrix of the characteristic image;
s3, correcting the characteristic image according to the state characteristic matrix of the characteristic image to obtain a standard surface image, and finishing image processing;
the step S2 comprises the following substeps:
s21, determining color weights of all pixel points according to RGB components of all pixel points in the feature image;
s22, constructing a state characteristic model, inputting the color weight of each pixel point into the state characteristic model, and determining the state characteristic value of each pixel point;
s23, generating a state feature matrix of the feature image according to the state feature values of the pixel points;
the state feature model comprises a depth convolution module, a global feature module and an output module which are sequentially connected;
the expression of the global feature module is as follows:wherein Q represents the output of the global feature module, C m Representing the output, K, of the mth convolution kernel in the depth convolution module m Represents the size, q, of the mth convolution kernel in the depth convolution module m Representing color weight corresponding to pixel point processed by mth convolution kernel in depth convolution module, B m The step length of the mth convolution kernel in the depth convolution module is represented, M represents the number of convolution kernels of the depth convolution module, sigma represents the standard deviation of all convolution kernel outputs, exp (·) represents an exponential function, and q represents the super-parameter of the global feature module;
the expression of the output module is as follows:wherein Z represents the output of the nth output layer in the output module, Q represents the output of the global feature module, R represents the red component of the pixel point corresponding to the nth output layer, G represents the green component of the pixel point corresponding to the nth output layer, B represents the blue component of the pixel point corresponding to the nth output layer, and ln (·) represents a logarithmic function;
in S23, the specific method for generating the state feature matrix is as follows: the method comprises the steps of taking the number of rows of pixel points of a feature image as the number of rows of a state feature matrix, taking the number of columns of pixel points of the feature image as the number of columns of the state feature matrix, taking the state feature value of each row of pixel points as the element of each row of the state feature matrix, and generating the state feature matrix of the feature image.
2. The method for processing a carbon nanotube preparation state image according to claim 1, wherein in S21, a color weight q of a pixel point in an ith row and a jth column in a feature image ij The calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein R is ij Representing the red component, G, of the ith row and jth column pixel points in the feature image ij Representing green component of ith row and jth column pixel points in characteristic image, B ij Representing blue component of pixel point in ith row and jth column in characteristic image, R 0 Representing the mean value of red components of all pixel points in the characteristic image, G 0 Representing the green component mean value of all pixel points in the characteristic image, B 0 Representing the mean of the blue components of all pixels in the feature image.
3. The method for processing a carbon nanotube preparation state image according to claim 1, wherein S3 comprises the sub-steps of:
s31, determining a red component correction coefficient, a green component correction coefficient and a blue component correction coefficient of each pixel point in the characteristic image according to the state characteristic matrix of the characteristic image;
s32, correcting the characteristic image according to the red component correction coefficient, the green component correction coefficient and the blue component correction coefficient of the characteristic image to obtain a standard surface image, and finishing image processing.
4. The method according to claim 3, wherein in S31, the correction coefficient of the red component of the ith row and jth column pixels in the feature imageThe calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein lambda represents the eigenvalue of the state eigenvalue matrix, R ij Representing the red component of the ith row and jth column pixel points in the feature image,/and (ii)>Representing an upward rounding, P 0 Representing maximum corresponding image of red component in characteristic imageThe position of the prime point, P ij Representing the position of the pixel point in the ith row and the jth column in the characteristic image, wherein dis (·) represents a Euclidean distance function;
in S31, the green component correction coefficient of the ith row and jth column pixel points in the feature imageThe calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein G is ij Representing green component, P of ith row and jth column pixel points in characteristic image 1 Representing the position of the pixel point corresponding to the maximum value of the green component;
in S31, the green component correction coefficient of the ith row and jth column pixel points in the feature imageThe calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein B is ij Representing blue component, P of pixel point in ith row and jth column in characteristic image 2 The position of the maximum value of the blue component corresponding to the pixel point is indicated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410128175.4A CN117649661B (en) | 2024-01-30 | 2024-01-30 | Carbon nanotube preparation state image processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410128175.4A CN117649661B (en) | 2024-01-30 | 2024-01-30 | Carbon nanotube preparation state image processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117649661A CN117649661A (en) | 2024-03-05 |
| CN117649661B true CN117649661B (en) | 2024-04-12 |
Family
ID=90043772
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410128175.4A Active CN117649661B (en) | 2024-01-30 | 2024-01-30 | Carbon nanotube preparation state image processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117649661B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118209565B (en) * | 2024-05-21 | 2024-08-13 | 青岛超瑞纳米新材料科技有限公司 | Intelligent monitoring method for processing process of carbon nano tube |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103079077A (en) * | 2011-10-26 | 2013-05-01 | 比亚迪股份有限公司 | Image processing method |
| WO2015109693A1 (en) * | 2014-01-22 | 2015-07-30 | 中兴通讯股份有限公司 | Method and system for image color calibration |
| CN106127817A (en) * | 2016-06-28 | 2016-11-16 | 广东工业大学 | A kind of image binaryzation method based on passage |
| CN107507250A (en) * | 2017-06-02 | 2017-12-22 | 北京工业大学 | A kind of complexion tongue color image color correction method based on convolutional neural networks |
| CN107578390A (en) * | 2017-09-14 | 2018-01-12 | 长沙全度影像科技有限公司 | A kind of method and device that image white balance correction is carried out using neutral net |
| CN108377373A (en) * | 2018-05-10 | 2018-08-07 | 杭州雄迈集成电路技术有限公司 | A kind of color rendition device and method pixel-based |
| CN108495101A (en) * | 2018-04-08 | 2018-09-04 | 北京大恒图像视觉有限公司 | A kind of method for correcting image, device, image capture device and readable storage medium storing program for executing |
| CN108600723A (en) * | 2018-07-20 | 2018-09-28 | 长沙全度影像科技有限公司 | A kind of color calibration method and evaluation method of panorama camera |
| CN109919994A (en) * | 2019-01-08 | 2019-06-21 | 浙江大学 | A shearer drum automatic height adjustment system based on deep learning image processing |
| CN110400275A (en) * | 2019-07-22 | 2019-11-01 | 中电健康云科技有限公司 | One kind being based on full convolutional neural networks and the pyramidal color calibration method of feature |
| CN111222445A (en) * | 2019-12-31 | 2020-06-02 | 江苏南高智能装备创新中心有限公司 | Straw detection system and method thereof |
| CN111292246A (en) * | 2018-12-07 | 2020-06-16 | 上海安翰医疗技术有限公司 | Image color correction method, storage medium, and endoscope |
| CN111310666A (en) * | 2020-02-18 | 2020-06-19 | 浙江工业大学 | High-resolution image ground feature identification and segmentation method based on texture features |
| CN112508812A (en) * | 2020-12-01 | 2021-03-16 | 厦门美图之家科技有限公司 | Image color cast correction method, model training method, device and equipment |
| CN114240782A (en) * | 2021-12-16 | 2022-03-25 | 北京爱芯科技有限公司 | Image correction method, system and electronic device |
| CN114266803A (en) * | 2021-12-21 | 2022-04-01 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN114331873A (en) * | 2021-12-07 | 2022-04-12 | 南京邮电大学 | Non-uniform illumination color image correction method based on region division |
| CN114463196A (en) * | 2021-12-28 | 2022-05-10 | 浙江大学嘉兴研究院 | Image correction method based on deep learning |
| CN116958534A (en) * | 2022-12-29 | 2023-10-27 | 腾讯科技（深圳）有限公司 | Image processing method, training method of image processing model and related device |
| CN116996786A (en) * | 2023-09-21 | 2023-11-03 | 清华大学 | RGB-IR image color recovery and correction method and device |
| CN117372431A (en) * | 2023-12-07 | 2024-01-09 | 青岛天仁微纳科技有限责任公司 | Image detection method of nano-imprint mold |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108282647B (en) * | 2018-01-31 | 2019-11-05 | 上海小蚁科技有限公司 | Color correcting method and device, computer readable storage medium, terminal |
-
2024
- 2024-01-30 CN CN202410128175.4A patent/CN117649661B/en active Active
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103079077A (en) * | 2011-10-26 | 2013-05-01 | 比亚迪股份有限公司 | Image processing method |
| WO2015109693A1 (en) * | 2014-01-22 | 2015-07-30 | 中兴通讯股份有限公司 | Method and system for image color calibration |
| CN106127817A (en) * | 2016-06-28 | 2016-11-16 | 广东工业大学 | A kind of image binaryzation method based on passage |
| CN107507250A (en) * | 2017-06-02 | 2017-12-22 | 北京工业大学 | A kind of complexion tongue color image color correction method based on convolutional neural networks |
| CN107578390A (en) * | 2017-09-14 | 2018-01-12 | 长沙全度影像科技有限公司 | A kind of method and device that image white balance correction is carried out using neutral net |
| CN108495101A (en) * | 2018-04-08 | 2018-09-04 | 北京大恒图像视觉有限公司 | A kind of method for correcting image, device, image capture device and readable storage medium storing program for executing |
| CN108377373A (en) * | 2018-05-10 | 2018-08-07 | 杭州雄迈集成电路技术有限公司 | A kind of color rendition device and method pixel-based |
| CN108600723A (en) * | 2018-07-20 | 2018-09-28 | 长沙全度影像科技有限公司 | A kind of color calibration method and evaluation method of panorama camera |
| CN111292246A (en) * | 2018-12-07 | 2020-06-16 | 上海安翰医疗技术有限公司 | Image color correction method, storage medium, and endoscope |
| CN109919994A (en) * | 2019-01-08 | 2019-06-21 | 浙江大学 | A shearer drum automatic height adjustment system based on deep learning image processing |
| CN110400275A (en) * | 2019-07-22 | 2019-11-01 | 中电健康云科技有限公司 | One kind being based on full convolutional neural networks and the pyramidal color calibration method of feature |
| CN111222445A (en) * | 2019-12-31 | 2020-06-02 | 江苏南高智能装备创新中心有限公司 | Straw detection system and method thereof |
| CN111310666A (en) * | 2020-02-18 | 2020-06-19 | 浙江工业大学 | High-resolution image ground feature identification and segmentation method based on texture features |
| CN112508812A (en) * | 2020-12-01 | 2021-03-16 | 厦门美图之家科技有限公司 | Image color cast correction method, model training method, device and equipment |
| CN114331873A (en) * | 2021-12-07 | 2022-04-12 | 南京邮电大学 | Non-uniform illumination color image correction method based on region division |
| CN114240782A (en) * | 2021-12-16 | 2022-03-25 | 北京爱芯科技有限公司 | Image correction method, system and electronic device |
| CN114266803A (en) * | 2021-12-21 | 2022-04-01 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN114463196A (en) * | 2021-12-28 | 2022-05-10 | 浙江大学嘉兴研究院 | Image correction method based on deep learning |
| CN116958534A (en) * | 2022-12-29 | 2023-10-27 | 腾讯科技（深圳）有限公司 | Image processing method, training method of image processing model and related device |
| CN116996786A (en) * | 2023-09-21 | 2023-11-03 | 清华大学 | RGB-IR image color recovery and correction method and device |
| CN117372431A (en) * | 2023-12-07 | 2024-01-09 | 青岛天仁微纳科技有限责任公司 | Image detection method of nano-imprint mold |
Non-Patent Citations (3)
| Title |
|---|
| EFFECTIVE COLOR CORRECTION PIPELINE FOR A NOISY IMAGE;Kenta Takahashi 等;《ICIP 2016》;20161231;4002-4006 * |
| 基于稠密卷积神经网络的遥感图像自动色彩校正;朱思捷 等;《中国科学院大学学报》;20190131;第36卷(第1期);93-100 * |
| 小波域彩色图像的混合噪声抑制算法;王小杰 等;《安庆师范学院学报(自然科学版)》;20161231(第04期);46-49 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117649661A (en) | 2024-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108537733B (en) | Super-resolution reconstruction method based on multi-path deep convolutional neural network | |
| CN112734646A (en) | Image super-resolution reconstruction method based on characteristic channel division | |
| CN117649661B (en) | Carbon nanotube preparation state image processing method | |
| US20210295477A1 (en) | Image inpainting method, image inpainting system and flat panel detector thereof | |
| CN102243711B (en) | A Method of Image Super-resolution Reconstruction Based on Neighborhood Nesting | |
| CN110232419A (en) | A kind of method of side slope rock category automatic identification | |
| CN108921783B (en) | A satellite image super-resolution reconstruction method based on hybrid loss function constraints | |
| CN110517272B (en) | Deep learning-based blood cell segmentation method | |
| CN110956581A (en) | Image modality conversion method based on dual-channel generation-fusion network | |
| CN111738954B (en) | A single-frame turbulent degraded image de-distortion method based on a double-layer hole U-Net model | |
| CN111210393B (en) | Color image enhancement method, system and storage medium based on edge extraction | |
| CN1573810A (en) | Image processing method and apparatus | |
| CN102436655A (en) | A SVD-based Super-resolution Reconstruction Image Quality Evaluation Method | |
| CN117156113A (en) | Deep learning speckle camera-based image correction method and device | |
| CN109933639A (en) | A Layer Stack-Oriented Adaptive Fusion Method of Multispectral Image and Panchromatic Image | |
| CN115908206A (en) | A Remote Sensing Image Dehazing Method Based on Dynamic Feature Attention Network | |
| CN106920213A (en) | The acquisition methods and system of a kind of high-definition picture | |
| CN117576139B (en) | Edge and corner detection method and system based on bilateral filtering | |
| CN110400320B (en) | A segmentation method of electrowetting defect pixels | |
| CN112184552A (en) | Sub-pixel convolution image super-resolution method based on high-frequency feature learning | |
| CN108288267A (en) | A kind of scanning electron microscope (SEM) photograph image sharpness based on dark is without with reference to evaluation method | |
| CN109146886B (en) | RGBD image semantic segmentation optimization method based on depth density | |
| CN108364274B (en) | Nondestructive clear reconstruction method of optical image under micro-nano scale | |
| CN116912086A (en) | Dual-path fusion-based image resolution improvement method and system | |
| CN116563142A (en) | Full-color sharpening frame acceleration method based on deep learning |
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 |