||加齢の影響を受ける Gabor 特徴を用いた顔画像からの年齢推定
562015-03-24 , 法政大学大学院理工学・工学研究科
In this study, we developed an estimation method for a face’s age that uses the Gabor features extracted from face images. We located a fixed number of feature points on each image from a face database by using two locating methods: visual observation and automatic by FaceAPI, and extracted the Gabor feature vectors from each of the allocated feature points. Among the components of the original feature vectors, we selected more age-sensitive ones to form a feature vector of the reduced dimensions. Subsequently, we obtained a regression equation to estimate age from facial images based on multiple regression analysis using the selected feature components as explanatory variables and each subject’s age as a response variable.