In the marketing field, it is very useful to collect the customer data of age and gender etc. For gender and age classification, this study focuses on the edge information that consists of all wrinkles in a face and also a neck. The rate of an average accurate classification is 74.5%.
色情報をベースに,顔画像から輪郭やしわなどのエッジ情報を抽出し,その情報を基に年代推定のコンピュータシミュレーションによる実験を行い,その有効性を述べた.
共同発表者:Miyoko Nakano, Fumiko Yasukata, Minoru Fukumi