Learning Representative Local Features for Face Detection

This paper describes a face detection approach via learning local features. The key idea is that local features, being manifested by a collection of pixels in a local region, are learnt from the training set instead of arbitrarily defined. The learning procedure consists of two steps. First, a modified version of NMF (Non-negative Matrix Factorization) is applied to get an overcomplete set of local features. Second, a learning algorithm based on AdaBoost is used to select a small number of local features and yields extremely efficient classifiers. Experiments are presented which show that the face detection performance is comparable to the state-of-the-art face detection systems.

• Type: Conference
• Year: 2001
• Where: CVPR
• Authors: Xiangrong Chen, Lie Gu, Stan Z. Li, HongJiang Zhang
• Keywords: Computer Vision, CVPR 2001, Face Detection Approach, Face Detection Performance, Local Features, Non-Negative Matrix Factorization, State-of-the-art Face Detection