Personal indentification based on a set of mirco facial feature point

2017 Fiscal Year Final Research Report

• Project/Area Number: 16K12453
• Research Category: Grant-in-Aid for Challenging Exploratory Research
• Allocation Type: Multi-year Fund
• Research Field: Perceptual information processing
• Research Institution: University of Tsukuba
• Principal Investigator: Fukui Kazuhiro 筑波大学, システム情報系, 教授 (40375423)
• Project Period (FY): 2016-04-01 – 2018-03-31
• Keywords: 顔認証 / 顔面微小特徴点 / 形状部分空間 / 正準角 / グラスマン判別分析

Outline of Final Research Achievements

In this research, we proposed a face identification method based on the 3-d structure of minute facial feature points, where the 3-d structure of each feature set is represented by a shape subspace in high dimensional vector space. To enhance the advanatge of the proposed method, we introduced Grassmann discriminant analysis to extract selectively features that are more useful for identifying, thereby performing more accurate identification. The effectiveness of the proposed method is demonstrated by evaluation experiments using actual facial video data.

Free Research Field

コンピュータビジョン