The main color structure setting of Chinese oil painting based on content analysis method

Author:

Chen Haiwei1

Affiliation:

1. 1 School of Arts and Crafts , Putian University , Putian , Fujian , , China .

Abstract

Abstract Based on the content analysis method, this paper first uses the PCA technique to disassemble and transform the base color information to extract multiple feature values. Secondly, the sparse autoencoder is used to adjust the feature parameters by training, and the activation function pair is used to calculate the confidence to complete the effective classification. Finally, the SVM algorithm is introduced to optimize the color information parameters, and the corresponding color label values are calculated by constructing a decision function to accurately set the pixel positions. The results show that the color difference value of Chinese oil painting image keeps between 0.5nbs -1.5nbs, the standard deviation value of saturation is 165.55, and the resolution is 610ppi, which indicates that the content-based analysis method can better coordinate and integrate the relationship between various color structures.

Publisher

Walter de Gruyter GmbH

Subject

Applied Mathematics,Engineering (miscellaneous),Modeling and Simulation,General Computer Science

Reference22 articles.

1. Du, S., Shi, Y., Hu, W., Wang, W., & Lian, J. (2020). Robust tensor factorization for color image and grayscale video recovery. IEEE Access, 8, 174410-174423.

2. Kanaeva, I. A., & Bolotova, Y. A. (2018). Color and luminance corrections for panoramic image stitching. Computer Optics, 42(5), 885-897.

3. Jimenez-Arredondo, V. H., Cepeda-Negrete, J., & Sanchez-Yanez, R. E. (2017). Multilevel color transfer on images for providing an artistic sight of the world. IEEE Access, 5, 15390-15399.

4. Wang, H., & Rong, J. (2017). Exploration of oil painting teaching in colleges and universities under the background of multi art culture development. Revista de la Facultad de Ingenieria, 32(16), 446-452.

5. Chen, L. (2017). Research on the application of semantic expression based on visual construction technology in oil painting teaching. Revista de la Facultad de Ingenieria, 32(16), 144-150.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3