Estimation of the Attractiveness of Food Photography Focusing on Main Ingredients

Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

Abstract: This research aims to develop a method to estimate the attractiveness of a food photo. The proposed method extracts two kinds of image features: 1) those focused on the appearance of the main ingredient, and 2) those focused on the impression of the entire food photo. The former is newly introduced in this paper, whereas the latter is based on previous research. The proposed method integrates these image features with a regression scheme to estimate the attractiveness of an arbitrary food photo. We have also built and released a food image dataset composed of images of ten food categories taken from 36 angles named NU FOOD 360x10. The images were assigned target values of their attractiveness through subjective experiments. Experimental results showed the effectiveness of integrating both kinds of image features.