Proceedings of the First International Conference on Science, Engineering and Technology Practices for Sustainable Development, ICSETPSD 2023, 17th-18th November 2023, Coimbatore, Tamilnadu, India

Research Article

Machine Vision Prediction Model for Product Color Design by Kansei Engineering

Download34 downloads
  • @INPROCEEDINGS{10.4108/eai.17-11-2023.2342794,
        author={Daocai  Han},
        title={Machine Vision Prediction Model for Product Color Design by Kansei Engineering},
        proceedings={Proceedings of the First International Conference on Science, Engineering and Technology Practices for Sustainable Development, ICSETPSD 2023, 17th-18th November 2023, Coimbatore, Tamilnadu, India},
        publisher={EAI},
        proceedings_a={ICSETPSD},
        year={2024},
        month={1},
        keywords={color design kansei engineering machine vision prediction model},
        doi={10.4108/eai.17-11-2023.2342794}
    }
    
  • Daocai Han
    Year: 2024
    Machine Vision Prediction Model for Product Color Design by Kansei Engineering
    ICSETPSD
    EAI
    DOI: 10.4108/eai.17-11-2023.2342794
Daocai Han1,*
  • 1: Shandong Institute of Commerce and Technology, Jinan 250103, Shandong, China
*Contact email: hdc202308@163.com

Abstract

Color is a visual element of people, it can bring people different levels, different feelings, and can make people have associations and emotional resonance. Under the background of Kansei engineering, product color design is an important research field. This paper aims to discuss the predictive model of Kansei engineering in product color design, in order to improve the quality of products and meet the needs of consumers. Through empirical research and user survey, this paper verifies the accuracy and effectiveness of product color perceptual image generated by machine vision prediction model for the elderly products. The survey and experimental results show that support vector machines perform best, with an accuracy of 91% and a recall rate 4% higher than BP neural networks.