Analysis of Impression from Design of Store Interior with Color Features Extracted by Semantic Segmentation

Abstract

The purpose of this study is to analyze the impression that a color image gives to a person and the color information contained in the image. In order to process a large amount of color images, we used a method of extracting representative colors from an image based on pixel information. In this study, we developed a method to combine image recognition technology using deep learning with representative color extraction technology, and analyzed the impression and color characteristics of design for store interior images. We collected color images of store interiors and keywords tagged with the images from web. Representative colors were extracted by a method using region division by deep learning. Furthermore, we quantized the characteristics of the representative colors included in the corresponding images. To examine those quantitative features of impressions, we conducted an experiment to compare subjective evaluation with calculated features and suggested that our calculated features reflect subjective evaluation.