An automatic face and facial feature points (FFPs) detection system is proposed. A face is represented as a graph where the nodes are placed at facial feature points (FFPs) labeled by their Gabor features and the edges describe their spatial relations. An innovative flexible feature matching is proposed to perform features correspondence between models and the input image. This matching model works like a random diffusion process in the image space by employing the locally competitive and globally corporative mechanism. The system works nicely on the face images under complicated background, pose variations and distorted by facial accessories. We demonstrate the benefits of our approach by its implementation on a face identification system.

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.