Objective Evaluation of Impression of Faces with Various Female Hairstyles Using Field of Visual Perception

Naoyuki AWANO  Kana MOROHOSHI  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E101-D   No.6   pp.1648-1656
Publication Date: 2018/06/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2018EDP7065
Type of Manuscript: PAPER
Category: Image Recognition, Computer Vision
Keyword: 
hairstyle,  facial shape,  field of visual perception,  kansei,  objective evaluation,  

Full Text: PDF(1.6MB)
>>Buy this Article


Summary: 
Most people are concerned about their appearance, and the easiest way to change the appearance is to change the hairstyle. However, except for professional hairstylists, it is difficult to objectively judge which hairstyle suits them. Currently, oval faces are generally said to be the ideal facial shape in terms of suitability to various hairstyles. Meanwhile, field of visual perception (FVP), proposed recently in the field of cognitive science, has attracted attention as a model to represent the visual perception phenomenon. Moreover, a computation model for digital images has been proposed, and it is expected to be used in quantitative evaluation of sensibility and sensitivity called “kansei.” Quantitative evaluation of “goodness of patterns” and “strength of impressions” by evaluating distributions of the field has been reported. However, it is unknown whether the evaluation method can be generalized for use in various subjects, because it has been applied only to some research subjects, such as characters, text, and simple graphics. In this study, for the first time, we apply FVP to facial images with various hairstyles and verify whether it has the potential of evaluating impressions of female faces. Specifically, we verify whether the impressions of facial images that combine various facial shapes and female hairstyles can be represented using FVP. We prepare many combinational images of facial shapes and hairstyles and conduct a psychological experiment to evaluate their impressions. Moreover, we compute the FVP of each image and propose a novel evaluation method by analyzing the distributions. The conventional and proposed evaluation values correlated to the psychological evaluation values after normalization, and demonstrated the effectiveness of the FVP as an image feature quantity to evaluate faces.