Pose invariant face recognition using biological inspired features based on ensemble of classifiers

摘要

This paper introduces a new method for view-independent face recognition by means of features inspired by the human's visual ventral stream and ensemble of classifiers. Several sets of scale and translation invariant features are first extracted. The feature vectors are then given to a new method of ensemble of classifiers. Diversity is a crucial condition for obtaining accurate ensembles. Diversity in our method is obtained by using bootstrapped replicas of the training vectors. Different training vectors are randomly drawn from the training vectors and are connected together to form diverse training sets. Experiments were performed to validate the method on the CMU-PIE and FERET face databases. Comparison with some of the most related methods indicates that the proposed method yields better recognition rate in view independent face recognition.