Title: Colour correction method of interior decoration engineering based on dense convolution neural network

Authors: Chuan-qin Zhang; Hong-tao Xing

Addresses: Jiangsu Vocational Institute of Architecture Technology, Xuzhou, 221116, China ' Jiangsu Vocational Institute of Architecture Technology, Xuzhou, 221116, China

Abstract: In order to solve the problem of long correction time existing in traditional methods, this paper proposes a colour correction method for interior decoration engineering based on dense convolutional neural network. For the colour deviation detection of interior decoration engineering, according to the detection results, the coordinated colour matching, colour matching harmony and visual comfort are taken as the colour correction objectives; and the calibration objective function is designed. The colour matching feature point and extreme point detection are carried out by using the objective function. According to the test results, the dense convolution neural network is used to correct the colour of interior decoration engineering and output the correction results. The experimental results show that the research method can improve the effect of colour correction, reduce the correction time, the mean error and the median error of colour deviation angle.

Keywords: dense convolution neural network; interior decoration engineering; colour correction; colour deviation.

DOI: 10.1504/IJART.2021.10043500

International Journal of Arts and Technology, 2021 Vol.13 No.2, pp.108 - 122

Received: 30 Nov 2020
Accepted: 21 Jun 2021

Published online: 21 Jan 2022 *

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