15 March 2006 2D/3D facial feature extraction
Author Affiliations +
We propose and compare three different automatic landmarking methods for near-frontal faces. The face information is provided as 480x640 gray-level images in addition to the corresponding 3D scene depth information. All three methods follow a coarse-to-fine suite and use the 3D information in an assist role. The first method employs a combination of principal component analysis (PCA) and independent component analysis (ICA) features to analyze the Gabor feature set. The second method uses a subset of DCT coefficients for template-based matching. These two methods employ SVM classifiers with polynomial kernel functions. The third method uses a mixture of factor analyzers to learn Gabor filter outputs. We contrast the localization performance separately with 2D texture and 3D depth information. Although the 3D depth information per se does not perform as well as texture images in landmark localization, the 3D information has still a beneficial role in eliminating the background and the false alarms.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hatice Çinar Akakin, Hatice Çinar Akakin, Albert Ali Salah, Albert Ali Salah, Lale Akarun, Lale Akarun, Bülent Sankur, Bülent Sankur, } "2D/3D facial feature extraction", Proc. SPIE 6064, Image Processing: Algorithms and Systems, Neural Networks, and Machine Learning, 60641D (15 March 2006); doi: 10.1117/12.643099; https://doi.org/10.1117/12.643099


3D face recognition via conformal representation
Proceedings of SPIE (March 05 2014)
Effects on facial expression in 3D face recognition
Proceedings of SPIE (March 27 2005)
Face recognition in complex backgrounds
Proceedings of SPIE (September 14 2004)
Local ICA for the Most Wanted face recognition
Proceedings of SPIE (April 04 2000)

Back to Top