Face recognition from a single view based on flexible neural network matching

This work presents a model-based face recognition approach that uses a hierarchical Gabor wavelet representation and flexible neural network matching. The representation of local features is based on the Gabor wavelets transform of a number of scales and a number of orientations. The Gabor wavelet representation is used in a innovative self-organization flexible neural network matching approach that can provide robust recognition. The sparse centers of Gabor wavelets in the images and neurons placement are arranged according to the hexagonal grids. Neural network matching between the model and the input image is to find out the exact correspondence of local features and to map the model to the input image based on local similarity and neighborhood grouping of local features. Experimental results in recognizing faces that includes the variations of translation, rotation in plane, rotation in depth, and slightly changes of facial expressions are also presented