A Machine Learning-Based Color Hierarchical Analysis Method for Chinese Painting and Calligraphy
A machine learning and color technology, applied in the field of pattern analysis, can solve problems such as unmanned
Inactive Publication Date: 2011-11-30
BEIJING UNION UNIVERSITY
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] At present, the research in the field of digital images of Chinese calligraphy and painting mainly focuses on the color restoration of Chinese calligraphy and painting, the analysis of the layout and composition of landscape paintings, and the classification of calligraphy and painting. set foot in
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0064] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.
[0065] At present, in the field of digital image processing of calligraphy and painting, the relevant research methods and ideas in the field of natural image processing are mainly used. For the extraction of feature descriptors of digital images of Chinese calligraphy and painting, at present, it mainly focuses on the global feature description of the image, but lacks the visual feature description information at the granular level of homogeneous regions. However, due to the similarities in painting techniques, composition, and color use of Chinese calligraphy and painting, as well as the inheritance of cultural history, the application of global features is limited to a certain extent. From the perspective of human visual perception analysis, regional-level description information can better distinguish the main body of Chinese calligraphy and paint...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a method for layered analysis of Chinese calligraphy and painting colors based on machine learning, which is characterized in that: performing pixel-level color classification on similar image samples, and establishing a set of prior knowledge about color sets; using the prior knowledge to The image is layered based on the color set; the semantic information contained in the image is layered on each of the color layers with each image area as a carrier; the segmentation and extraction of each element of the image is realized; the steps include 1) obtain the color prior knowledge of digital image; 2) establish the original color description model of color layering with machine learning method; 3) carry out feedback learning to described original color description model, obtain color description model; 4) use all The color description model described above performs color layering on the input calligraphy and painting digital images. The method of the present invention has laid a foundation for realizing the segmentation and extraction of various elements of Chinese calligraphy and painting works, such as technique, classification, composition, theme, and even artistic conception and other middle and high-level semantic research.
Description
technical field [0001] The invention relates to the field of pattern analysis, in particular to a method for layered analysis of Chinese calligraphy and painting colors based on machine learning. Background technique [0002] Chinese calligraphy and painting works are an important part of Chinese culture, with a unique form of artistic creation, forming a system of its own in the field of world art, and becoming a school of its own. Since the 1990s, with the rapid development of computer technology and image processing technology, digital images of Chinese calligraphy and painting works have been widely used, so the processing and use of digital images of Chinese calligraphy and painting works has received more and more attention. [0003] At present, the research on images is mainly concentrated in the field of natural images, and the technology is relatively mature. Its main research areas include annotation and classification based on image semantics, image segmentation,...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/66G06N1/00G06N99/00
Inventor 娄海涛胡正坤鲍泓王迪菲王真真张南
Owner BEIJING UNION UNIVERSITY