Overview of automatic facial expressions analysis
VIIP '07 The Seventh IASTED International Conference on Visualization, Imaging and Image Processing
An eye detection system based on neural autoassociators
ANNPR'06 Proceedings of the Second international conference on Artificial Neural Networks in Pattern Recognition
Hi-index | 0.00 |
In this paper we present a new approach to theproblem of detecting the eyes from a still facial image.Features such as color, edges, intensity and shape areincorporated in different stages of our method. First, theface region is extracted from the image by skin-colorfilter and window growing. Second, eyes areapproximately located by projection of gradient featuresin different directions. Third, the eyes could be extractedif it is required by some specific applications. Part of theAR Database has been used for experiments andbenchmarking. For subjects not wearing glasses, the eyescould be correctly located in 91.56% of the images and inover 90% of these images they could be accuratelyextracted, while for subjects wearing glasses, the successrate is somewhat lower.