Title :
Learning probabilistic distribution model for multi-view face detection
Author :
Gu, Lie ; Li, Stan Z. ; Zhang, Hong-Jiang
Author_Institution :
Microsoft Res. China, Beijing, China
Abstract :
Modeling subspaces of a distribution of interest in high dimensional spaces is a challenging problem in pattern analysis. In this paper, we present a novel framework for pose invariant face detection through. multi-view face distribution modeling. The approach is aimed to learn a set of low-dimensional subspaces from an originally nonlinear distribution by using the mixtures of probabilistic PCA. From the experiments, we found the learned PPCA models are of low dimensionality and exhibit high local linearity, and consequently offer an efficient representation for visual recognition. The model is then used to extract features and select "representative" negative training samples. Multi-view face detection is performed in the derived feature space by classifying each face into one of the view classes or into the nonface class, by using a multi-class SVM array classifier. The classification results from each view are fused together and yields the final classification results. The experimental results demonstrate the performance superiority of our proposed framework while performing multi-view face detection.
Keywords :
face recognition; feature extraction; image classification; learning (artificial intelligence); learning automata; principal component analysis; probability; face classification; feature extraction; feature space; high dimensional spaces; learning probabilistic distribution model; low-dimensional subspaces; multi-class SVM array classifier; multi-view face detection; multi-view face distribution modeling; negative training samples; nonlinear distribution; pattern analysis; pose invariant face detection; probabilistic PCA; subspace modeling; visual recognition; Algorithm design and analysis; Face detection; Face recognition; Feature extraction; Layout; Lighting; Linearity; Principal component analysis; Support vector machine classification; Support vector machines;
Conference_Titel :
Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on
Print_ISBN :
0-7695-1272-0
DOI :
10.1109/CVPR.2001.990934