Combining feature optimization into neural network based face detection
Qian Gu, Shao-Ying Li · 2002
A system using feature optimization and neural learning techniques is presented for detection of upright frontal faces. The feature set is optimized in terms of the Fisher's linear discrimination (FLD) criterion. A neural network (NN) method is used to learn a complex mapping function for the classification, given the optimized feature set. The optimization of feature set reduces the burden of the subsequent NN classifier and improves its performance in learning speed and classification rates. Experimental results show that the feature set optimized by using the FLD transform significantly improves the detection rate while maintaining the same false alarms. Our system produces higher detection and lower missing rates than several existing state-of-the-art face detection systems, with an average false detection rate.