CN111476831B - PCB image color migration device and method based on cluster analysis - Google Patents
PCB image color migration device and method based on cluster analysis Download PDFInfo
- Publication number
- CN111476831B CN111476831B CN202010202750.2A CN202010202750A CN111476831B CN 111476831 B CN111476831 B CN 111476831B CN 202010202750 A CN202010202750 A CN 202010202750A CN 111476831 B CN111476831 B CN 111476831B
- Authority
- CN
- China
- Prior art keywords
- color
- image
- cluster
- module
- pcb
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
- Color Image Communication Systems (AREA)
Abstract
The invention provides a PCB image color migration device and a method based on cluster analysis, wherein the device comprises the following steps: the image acquisition module acquires a source image and a target image; the RGB color map acquisition module is used for respectively acquiring RGB color maps converted from a source image and a target image; the color space conversion module converts the RGB color map into an LAB color map; the color clustering module sets and clusters the LAB color pictures by utilizing the number of the color clusters to generate a color cluster category list; the color cluster matching module performs PCB bipartite graph matching on the list of the source image and the target image to obtain a matching result; the color mapping module calculates a transformation matrix according to the matching result, and maps the LAB color map to a new color according to the matrix; the color space inverse transform module converts the mapped colors into an RGB color-migrated image. The device divides the colors in the images into different categories by utilizing the clusters, performs color migration aiming at the colors of the different categories, and achieves good effect of image registration.
Description
Technical Field
The invention relates to the technical field of computer software engineering, in particular to a novel technology for carrying out color migration on different images, namely a PCB image color migration device and method based on cluster analysis.
Background
The color migration aims to adjust the color of the source picture according to the target picture so that the color of the source image is matched with the target image as much as possible. A common color migration algorithm is to determine a linear transformation based on statistical analysis of the rendered image such that the target image and the original image have the same mean and variance in the l, α, β space. The algorithm is based on overall color migration and does not work well for images of multi-color content. If the colors of the two images are very different, the l, alpha, beta spatial color channels can enlarge the chromaticity difference, and the images are not ideal as a result.
The color migration of the PCB (Printed Circuit Board ) produced at different times by the same manufacturing process flow is to correct the colors of the images shot by different environments (illumination intensity, illumination uniformity, light source color, background noise and the like) of the PCB so as to match the colors of the standard templates. By using the traditional color migration method, the colors of the metal part and the substrate part are mutually influenced on the channel level, the matching effect is poor, and a lot of variegates appear.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems in the related art to some extent.
Therefore, an object of the present invention is to provide a PCB image color migration apparatus based on cluster analysis.
Another object of the present invention is to provide a method for migrating colors of PCB images based on cluster analysis, which performs color migration for different types of colors, so that the image registration achieves a very good effect.
In order to achieve the above object, an embodiment of an aspect of the present invention provides a PCB image color migration apparatus based on cluster analysis, including: the image acquisition module is used for respectively acquiring a PCB source image and a PCB target image; the RGB color image acquisition module is connected with the image acquisition module and used for respectively acquiring and converting the PCB source image and the PCB target image into RGB color images; the color space transformation module is connected with the RGB color map acquisition module and used for converting the RGB color map into an LAB color map; the color clustering module is connected with the color space transformation module and is used for setting the types of color clusters according to the LAB color images, and clustering the LAB color images by utilizing the color clusters to obtain a color cluster type list, wherein the color cluster type list comprises a source image color cluster type list and a target image color cluster type list; the color cluster matching module is connected with the color cluster module and the image acquisition module and is used for performing bipartite graph matching on the source image color cluster category list and the target image color cluster category list to obtain a color cluster matching result; the color mapping module is connected with the color cluster matching module and the color space module and is used for providing a source image in an LAB format according to the color space conversion module, calculating a color conversion matrix by the color cluster matching module, calculating a color conversion matrix according to the color cluster matching result, mapping the LAB color map to a new color according to the color conversion matrix and generating an image after LAB color migration; and the color space inverse transformation module is connected with the color mapping module and is used for converting the LAB color migrated image into an RGB color migrated image.
The PCB image color migration device based on cluster analysis realizes adjustment and correction of the PCB image color to be detected in the PCB detection positioning device, does not need to operate the mean value and variance of the image channel, but performs local color matching, and has more accurate effect; and the main colors can be subjected to local color matching, so that interference among different colors is reduced, and the false colors are removed.
In addition, the PCB image color migration apparatus based on cluster analysis according to the above embodiment of the present invention may further have the following additional technical features:
further, in one embodiment of the present invention, the color space conversion module is specifically configured to:
converting the RGB color map into an LMS space to obtain an LMS color map;
and converting the LMS color map into an LAB space to obtain an LAB color map.
Further, in one embodiment of the present invention, the color clustering module uses a correlation clustering algorithm, such as SVM, bayes, KMeans, mean shift, DBSCAN, gaussian mixture model, and other clustering algorithms, to perform color clustering analysis on the PCB image.
Further, in one embodiment of the present invention, the color cluster matching module is specifically configured to:
matching the color cluster of each source image in the source image color cluster category list to the color cluster of only one target image in the target image color cluster category list, and outputting the color cluster matching result.
Further, in one embodiment of the present invention, a related color transformation formula, such as a calculation formula, is utilized, but not limited to:
wherein u is src R is the mean value of the color clusters of the source image src For the variance of the color clusters of the source image, u dst R is the mean value of the color cluster of the target image dst Is the variance of the target image color cluster. And mapping the LAB color image in the color mapping module to a new color.
In order to achieve the above objective, another embodiment of the present invention provides a method for migrating colors of a PCB image based on cluster analysis, comprising the steps of: step S1, respectively acquiring a PCB source image and a PCB target image color chart; s2, respectively converting the PCB source image and the PCB target image into RGB color images; step S3, converting the RGB color map into an LAB color map; step S4, setting the types of color clusters according to the LAB color map, and clustering the LAB color map by utilizing the color clusters to obtain a color cluster type list, wherein the color cluster list comprises a source image color cluster type list and a target image color cluster type list; step S5, performing bipartite graph matching on the step S1 by using the source image color cluster category list and the target image color cluster category list to obtain a color cluster matching result; step S6, calculating a color transformation matrix according to the color cluster matching result, mapping the LAB color map to a new color according to the color transformation matrix, and generating an LAB color migrated image; and step S7, converting the LAB color-migrated image into an RGB color-migrated image.
The PCB image color migration method based on cluster analysis realizes adjustment and correction of the PCB image color to be detected in the PCB detection positioning device, does not need to operate the mean value and variance of the image channel, but performs local color matching, and has more accurate effect; and the main colors can be subjected to local color matching, so that interference among different colors is reduced, and the false colors are removed.
In addition, the method for migrating colors of PCB images based on cluster analysis according to the embodiment of the invention can also have the following additional technical features:
further, in an embodiment of the present invention, the converting the RGB color map into an LAB color map further includes: converting the RGB color map into an LMS space to obtain an LMS color map; and converting the LMS color map into an LAB space to obtain an LAB color map.
Further, in one embodiment of the invention, the PCB image color is clustered using a correlation clustering algorithm, such as SVM, bayes, KMeans, mean shift, DBSCAN, gaussian mixture model, and other clustering algorithms.
Further, in an embodiment of the present invention, in the process of matching the bipartite graph: matching the color cluster of each source image in the source image color cluster category list to the color cluster of only one target image in the target image color cluster category list, and outputting the color cluster matching result.
Further, in one embodiment of the present invention, a related color transformation formula, such as a calculation formula, is utilized, but not limited to:
wherein u is src R is the mean value of the color clusters of the source image src For the variance of the color clusters of the source image, u dst R is the mean value of the color cluster of the target image dst Is the variance of the target image color cluster. And mapping the LAB color image in the color mapping module to a new color.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a schematic view of a PCB image color migration apparatus based on cluster analysis according to one embodiment of the present invention;
FIG. 2 is a schematic illustration of an implementation of a cluster analysis based PCB image color migration apparatus according to one specific example of the present invention;
fig. 3 is a flowchart of a method for color migration of PCB images based on cluster analysis according to one embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
The following describes a device and a method for migrating colors of a PCB image based on a cluster analysis according to an embodiment of the present invention with reference to the accompanying drawings, and first describes a device for migrating colors of a PCB image based on a cluster analysis according to an embodiment of the present invention with reference to the accompanying drawings.
Fig. 1 is a schematic structural diagram of a PCB image color migration apparatus based on cluster analysis according to an embodiment of the present invention.
As shown in fig. 1, the apparatus 10 includes: an image acquisition module 101, an RGB color map acquisition module 102, a color space transformation module 103, a color clustering module 104, a color cluster matching module 105, a color mapping module 106, and a color space inverse transformation module 107.
The image acquisition module 101 is used for respectively acquiring a PCB source image and a PCB target image.
And the RGB color image acquisition module 102 is connected with the image acquisition module and is used for respectively acquiring and converting the PCB source image and the PCB target image into RGB color images.
The color space transformation model 103 is linked to the RGB color map acquisition module 102 for converting the RGB color map into a LAB color map.
Further, in one embodiment of the present invention, the color space transform module 103 is specifically configured to:
converting the RGB color map into an LMS space to obtain an LMS color map;
and converting the LMS color map into an LAB space to obtain the LAB color map.
Specifically, as shown in fig. 2, the RGB color map acquired by the RGB color map acquisition module 102 is input into the color space conversion module 103, and then is converted according to a related color image transformation formula, but not limited to this formula, such as:
that is, the RGB color map is converted into the LMS space, and then converted from the LMS space into the LAB space, so as to obtain the LAB color map, where A, B, C is a suitable transformation matrix.
The color clustering module 104 is connected to the color space transformation module 103, and is configured to set a type of a color cluster according to the LAB color map, and cluster the LAB color map by using the color cluster to obtain a color cluster type list, where the color cluster type list includes a source image color cluster type list and a target image color cluster type list.
That is, all Lab colors in the image are clustered, and the color cluster class is output.
Further, in one embodiment of the invention, the color clustering module 104 performs color clustering analysis on the PCB images using a correlation clustering algorithm, such as SVM, bayes, KMeans, mean shift, DBSCAN, gaussian mixture model, and other clustering algorithms.
Specifically, as shown in fig. 2, the LAB color map obtained in the color space transformation module 103 is input into the color clustering module 104, each element can be regarded as a triplet (L, a, b) according to color clustering, three-dimensional space clustering (for example: SVM, bayes, KMeans, mean shift, DBSCAN, gaussian mixture model, etc.) is performed, and then the number N of color clusters is set for the types of the main colors in the LAB color map, so that each color cluster is each type of clustering result, and a color cluster type list is obtained.
The color cluster matching module 105 is connected with the color cluster module 104 and the image acquisition module 101, and is used for performing bipartite graph matching on the image acquisition module 101 by using the source image color cluster category list and the target image color cluster category list to obtain a color cluster matching result.
That is, the color clusters in the PCB source image and the PCB target image are binary matched.
Further, in one embodiment of the present invention, the color cluster matching module 105 is specifically configured to:
matching the color cluster of each source image in the source image color cluster category list to the color cluster of only one target image in the target image color cluster category list, and outputting a color cluster matching result.
Specifically, as shown in fig. 2, the source image color cluster category list and the target image color cluster category list obtained in the color clustering module 104 are input into the color cluster matching module 105, bipartite graph matching is performed on the image acquisition module 103, the color clusters of each source image in the source image color cluster category list are matched to the color cluster of a unique target image, and finally all matched results are output. It should be noted that any two sides that are matched do not depend on the same cluster.
The color mapping module 106 is connected to the color cluster matching module 105 and the color space transformation module 103, and is configured to provide a source image in LAB format according to the color space transformation module, calculate a color transformation matrix by the color cluster matching module 105, calculate a color transformation matrix according to a color cluster matching result, map the LAB color map to a new color according to the color transformation matrix, and generate an LAB color migrated image.
That is, a color transformation matrix is calculated from two color clusters connected by each match, and then all pixels in the source image are mapped to a new color according to the transformation matrix from the color cluster to which they belong.
Further, in one embodiment of the invention,
using a related color transformation formula, such as, but not limited to, a calculation formula:
wherein u is src R is the mean value of the color clusters of the source image src For the variance of the color clusters of the source image, u dst R is the mean value of the color cluster of the target image dst Is the variance of the target image color cluster. And mapping the LAB color image in the color mapping module to a new color.
It may be understood that the color cluster matching result obtained in the color cluster matching module 105 is input to the color mapping module 106 to process two color clusters (source image-target image) corresponding to each match in the color cluster matching result, and any color (l, a, b) belonging to the color cluster is converted, and the obtained and output converted image is specifically expressed by, but not limited to, the formula:
wherein u is src R is the mean value of the color clusters of the source image src For the variance of the color clusters of the source image, u dst R is the mean value of the color cluster of the target image dst For the variance of the target image color cluster, X may be any channel of L, a, b, and the corresponding mean and variance are also the values of the corresponding channels.
The color space inverse transform module 107 is coupled to the color mapping module 106 for converting the LAB color-migrated image into an RGB color-migrated image.
That is, the LAB color-migrated image obtained in the color mapping module 106 is input to the LAB color space inverse transformation module 107, and the LAB color-migrated image is converted into the RGB color-migrated image, that is, the inverse transformation is performed, contrary to the process of the color space conversion module 103, to output the RGB color-migrated image.
According to the PCB image color migration device based on the clustering analysis, the clustering algorithm is utilized to perform the clustering analysis on the colors in the image, then the local color matching is performed on the main colors, the interference among different colors is reduced, the false colors are removed, meanwhile, the mean value and the variance of the image channel are not required to be operated, and the local colors are matched, so that the effect is more accurate.
Next, a method for migrating colors of PCB images based on cluster analysis according to an embodiment of the present invention will be described with reference to the accompanying drawings.
Fig. 3 is a flowchart of a method for color migration of a PCB image based on cluster analysis according to an embodiment of the present invention.
As shown in fig. 3, the method for migrating colors of PCB images based on cluster analysis comprises the following steps:
in step S1, a PCB source image and a PCB target image color chart are respectively acquired.
In step S2, the PCB source image and the PCB target image are respectively transformed into RGB color images.
In step S3, the RGB color map is converted into a LAB color map.
Further, in one embodiment of the present invention, converting the RGB color map into the LAB color map further includes: converting the RGB color map into an LMS space to obtain an LMS color map; and converting the LMS color map into an LAB space to obtain the LAB color map.
In step S4, the types of the color clusters are set according to the LAB color map, and the LAB color map is clustered by using the color clusters to obtain a color cluster type list, where the color cluster list includes a source image color cluster type list and a target image color cluster type list.
Further, in one embodiment of the invention, the PCB image color is clustered using a correlation clustering algorithm, such as SVM, bayes, KMeans, mean shift, DBSCAN, gaussian mixture model, and other clustering algorithms.
In step S5, the source image color cluster category list and the target image color cluster category list are subjected to bipartite graph matching on the PCB source image and the PCB target image, and a color cluster matching result is obtained.
Further, in one embodiment of the present invention, during bipartite graph matching:
and matching the color cluster of each source image in the source image color cluster list to the color cluster of only one target image in the target image color cluster list, and outputting a color cluster matching result.
In step S6, a color transformation matrix is calculated according to the color cluster matching result, and the LAB color map is mapped to a new color according to the color transformation matrix, so as to generate an LAB color migrated image.
Further, in one embodiment of the present invention, the LAB color map is mapped to a new color, and the calculation formula is, but not limited to, the formula:
wherein u is src R is the mean value of the color clusters of the source image src For the variance of the color clusters of the source image, u dst R is the mean value of the color cluster of the target image dst Is the variance of the target image color cluster.
In step S7, the LAB color-migrated image is converted into an RGB color-migrated image.
According to the PCB image color migration method based on the clustering analysis, the clustering algorithm is utilized to perform clustering analysis on the colors in the image, then partial color matching is performed on the main colors, interference among different colors is reduced, false colors are removed, meanwhile, the mean value and variance of an image channel are not required to be operated, and the partial colors are matched, so that the effect is more accurate.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (4)
1. A cluster analysis-based PCB image color migration apparatus, comprising:
the image acquisition module is used for respectively acquiring a PCB source image and a PCB target image;
the RGB color image acquisition module is connected with the image acquisition module and used for respectively acquiring and converting the PCB source image and the PCB target image into RGB color images;
the color space conversion module is connected with the RGB color map acquisition module and used for converting the RGB color map into an LAB color map, converting the RGB color map into an LMS space to obtain an LMS color map, and converting the LMS color map into the LAB space to obtain a PCB image to be tested and a PCB standard board LAB color map;
the color clustering module is connected with the color space transformation module and is used for setting the types of color clusters according to the LAB color images, and clustering the LAB color images by utilizing the color clusters to obtain a color cluster type list, wherein the color cluster type list comprises a source image color cluster type list and a target image color cluster type list, and the color cluster types in the color cluster type list are output after all LAB colors in the images are clustered;
the color cluster matching module is connected with the color cluster module and the image acquisition module and is used for carrying out bipartite graph matching on the image acquisition module by the source image color cluster type list and the target image color cluster type list, and matching the color clusters of each source image in the source image color cluster type list to the color clusters of a unique target image to obtain a color cluster matching result;
the color mapping module is connected with the color cluster matching module and the color space transformation module and is used for providing a source image in an LAB format according to the color space transformation module, calculating a color transformation matrix according to the color cluster matching result by the color cluster matching module, mapping the LAB color map to a new color according to the color transformation matrix and generating an image after LAB color migration; and
and the color space inverse transformation module is connected with the color mapping module and is used for converting the LAB color migrated image into an RGB color migrated image.
2. The device for color migration of PCB images based on cluster analysis of claim 1, wherein the color clustering module uses any of a correlation clustering algorithm SVM, bayes, KMeans, a mean shift, a DBSCAN, a gaussian mixture model to perform cluster analysis on PCB image colors, but is not limited to the above algorithm.
3. The cluster analysis based PCB image color migration apparatus of claim 1, wherein the color cluster matching module is further configured to:
and outputting the color cluster matching result.
4. The cluster analysis based PCB image color migration apparatus of claim 1, wherein the LAB color map is mapped to a new color using a related color transformation formula, wherein the calculation formula of the related color transformation formula is, but not limited to, the formula:
wherein u is src R is the mean value of the color clusters of the source image src For the variance of the color clusters of the source image, u dst R is the mean value of the color cluster of the target image dst Is the variance of the target image color cluster.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010202750.2A CN111476831B (en) | 2020-03-20 | 2020-03-20 | PCB image color migration device and method based on cluster analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010202750.2A CN111476831B (en) | 2020-03-20 | 2020-03-20 | PCB image color migration device and method based on cluster analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111476831A CN111476831A (en) | 2020-07-31 |
| CN111476831B true CN111476831B (en) | 2023-07-18 |
Family
ID=71747672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010202750.2A Active CN111476831B (en) | 2020-03-20 | 2020-03-20 | PCB image color migration device and method based on cluster analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111476831B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112149718B (en) * | 2020-09-03 | 2023-03-14 | 济南信通达电气科技有限公司 | Power transmission channel hidden danger target amplification method and equipment |
| CN112950461A (en) * | 2021-03-27 | 2021-06-11 | 刘文平 | Global and superpixel segmentation fused color migration method |
| CN114627016A (en) * | 2022-03-15 | 2022-06-14 | 厦门微亚智能科技有限公司 | Industrial defect detection preprocessing method based on color migration strategy |
| CN114863095B (en) * | 2022-03-25 | 2023-11-28 | 电子科技大学 | Answer sheet image segmentation method based on color conversion |
| CN115587930B (en) * | 2022-12-12 | 2023-04-18 | 成都索贝数码科技股份有限公司 | Image color style migration method, device and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120040004A (en) * | 2010-10-18 | 2012-04-26 | 전남대학교산학협력단 | System for color clustering based on tensor voting and method therefor |
| CN103617596A (en) * | 2013-10-12 | 2014-03-05 | 中山大学 | Image color style transformation method based on flow pattern transition |
| KR20160031873A (en) * | 2014-09-15 | 2016-03-23 | 연세대학교 산학협력단 | Gesture recognizer setting method, gesture recognition method and apparatus |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105261046B (en) * | 2015-09-23 | 2018-01-19 | 北京航空航天大学 | A kind of tone moving method of scene adaptive |
| CN109710791A (en) * | 2018-12-14 | 2019-05-03 | 中南大学 | A kind of multi-source color image color moving method based on significant filter |
-
2020
- 2020-03-20 CN CN202010202750.2A patent/CN111476831B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120040004A (en) * | 2010-10-18 | 2012-04-26 | 전남대학교산학협력단 | System for color clustering based on tensor voting and method therefor |
| CN103617596A (en) * | 2013-10-12 | 2014-03-05 | 中山大学 | Image color style transformation method based on flow pattern transition |
| KR20160031873A (en) * | 2014-09-15 | 2016-03-23 | 연세대학교 산학협력단 | Gesture recognizer setting method, gesture recognition method and apparatus |
Non-Patent Citations (2)
| Title |
|---|
| 基于Lab空间的K均值聚类彩色图像分割;吴迪;刘伟峰;胡胜;胡灵芝;胡俊华;;电子科技(第10期);全文 * |
| 基于高斯混合模型的区域颜色迁移;向遥;李宏;谢政;张卫;;中国图象图形学报(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111476831A (en) | 2020-07-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111476831B (en) | PCB image color migration device and method based on cluster analysis | |
| US6594384B1 (en) | Apparatus and method for estimating and converting illuminant chromaticity using perceived illumination and highlight | |
| Ng et al. | Using geometry invariants for camera response function estimation | |
| CN112689140B (en) | White balance synchronization method and device, electronic equipment and storage medium | |
| KR100734935B1 (en) | Area segmentation of an image | |
| Joze et al. | White patch gamut mapping colour constancy | |
| CN114723044B (en) | Error compensation method, device, chip and equipment for in-memory computing chip | |
| JP2009117991A (en) | Image conversion apparatus and image conversion program | |
| US10504245B2 (en) | Image processing device and method for color balancing | |
| JP2004166182A (en) | White dot, white spot variation estimation method of white balance point | |
| JP2008092565A (en) | Color matching method and image capturing device | |
| CN114930381A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN116489330A (en) | Self-adaptive white balance method and device, electronic equipment and storage medium | |
| CN115587948A (en) | Image dark field correction method and device | |
| CN109242809A (en) | A kind of point cloud filtering system and filtering method based on RGB-D information | |
| CN114463221A (en) | Self-supervision color correction method for multi-device domain AWB enhancement | |
| CN114627016A (en) | Industrial defect detection preprocessing method based on color migration strategy | |
| CN110047415B (en) | Color gamut mapping method, electronic device and storage medium | |
| Lam et al. | Automatic white balancing using adjacent channels adjustment in RGB domain | |
| CN112907485B (en) | Remote sensing image batch toning method based on lalpha beta space color mapping | |
| CN101237517B (en) | Image processing method and device | |
| JPH07274019A (en) | Picture evaluation method and color picture input device | |
| CN117768791B (en) | Cross-camera image white balance method and system based on neural network | |
| CN114414065B (en) | Object temperature detection method, device, computer equipment and medium | |
| CN116912080A (en) | Image color migration method and device based on texture features |
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 |