Share Email Print

Proceedings Paper

Video-based face identification using unconstrained non-linear composite filters
Author(s): Everardo Santiago-Ramírez; J.-A. Gonzalez-Fraga; J.-I. Ascencio-Lopez; Sixto Lazaro-Martinez
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper considers the face identification task in video sequences where the individual’s face presents variations; such as expressions, pose, scale, shadow/lighting and occlusion. The principles of Synthetic Discriminant Functions (SDF) and K-Law filters are used to design an adaptive unconstrained correlation filter (AUNCF). We developed a face tracking algorithm which together with a face recognition algorithm were carefully integrated into a video-based face identification method. First, a manually selected face in the first video frame is identified. Then, in order to build an initial correlation filter, the selected face is distorted so that it generates a training set. Finally, the face tracking task is performed using the initial correlation filter which is updated through the video sequence. The efficiency of the proposed method is shown by experiments on video sequences, where different facial variations are presented. The proposed method correctly identifies and tracks the face under observation on the tested video sequences.

Paper Details

Date Published: 15 October 2012
PDF: 9 pages
Proc. SPIE 8499, Applications of Digital Image Processing XXXV, 84991Z (15 October 2012); doi: 10.1117/12.930223
Show Author Affiliations
Everardo Santiago-Ramírez, Univ. Autónoma de Baja California (Mexico)
J.-A. Gonzalez-Fraga, Univ. Autónoma de Baja California (Mexico)
J.-I. Ascencio-Lopez, Univ. Autónoma de Baja California (Mexico)
Sixto Lazaro-Martinez, Univ. Autónoma de Baja California (Mexico)

Published in SPIE Proceedings Vol. 8499:
Applications of Digital Image Processing XXXV
Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top