Title: Colour deviation correction method of art image based on fuzzy classification

Authors: Gaozhan Liu; Feng Gao

Addresses: Art College, Hunan City University, YiYang 413000, China ' School of Artificial Intelligence, Chongqing University of Arts and Sciences, Chongqing 402160, China

Abstract: In order to solve the problems of low correction accuracy and large classification error of deviation data in traditional colour deviation correction methods, a colour deviation correction method of art image based on fuzzy classification is proposed in this paper. Firstly, the logarithm space of RGB component and colour feature of art image colour is determined to complete the colour feature extraction of art image. Then, the consistency of colour feature data is unified by norm discretisation. Finally, the maximum membership of colour feature data is calculated, and the fuzzy subset is processed in discrete domain to complete the classification of colour deviation data of art image. Further calculate the membership degree of the deviation data to be corrected to complete the colour deviation correction of art image. The experimental results show that the accuracy of the proposed method is high, and the classification error of deviation data is small.

Keywords: fuzzy classification; art image; colour deviation correction; membership degree; norm discretisation.

DOI: 10.1504/IJART.2022.128468

International Journal of Arts and Technology, 2022 Vol.14 No.3, pp.224 - 235

Received: 07 Apr 2022
Accepted: 28 Oct 2022
Published online: 23 Jan 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article