Premium
High‐Speed multiview face localization and tracking with a minimum bounding box using genetic algorithm
Author(s) -
Sato Junya,
Akashi Takuya
Publication year - 2017
Publication title -
ieej transactions on electrical and electronic engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.254
H-Index - 30
eISSN - 1931-4981
pISSN - 1931-4973
DOI - 10.1002/tee.22460
Subject(s) - minimum bounding box , computer vision , face (sociological concept) , artificial intelligence , computer science , tracking (education) , affine transformation , facial motion capture , genetic algorithm , bounding overwatch , transformation (genetics) , template matching , facial recognition system , algorithm , face detection , image (mathematics) , pattern recognition (psychology) , mathematics , psychology , social science , pedagogy , biochemistry , chemistry , sociology , machine learning , pure mathematics , gene
In this paper, we propose a high‐speed multiview face localization and tracking method with a minimum bounding box using template matching with genetic algorithm (GA). In this method, a head is treated as a cylinder, and the multiview face can be represented using the development of lateral surface (two‐dimensional (2D) model). The face can be localized by a template, which is generated from the model and corresponds to the target face direction. Processing is very fast because the parameters for both template generation and affine transformation are simultaneously optimized by GA. In the experiment, challenging 60‐video sequences are created in a situation where subjects drastically move their faces in a room, using a standard computer and web camera. Then, the proposed method is applied to the sequences, and the performance is investigated. As a result, the proposed method achieves fast and accurate multiview face localization and tracking. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.