A hybrid method for facial recognition systems

This paper proposes a highly robust method for face recognition. Techniques introduced in this work are composed of two stages. Firstly, the feature of face is to be detected by the combined of trace transform and fast active contour. Then, in the second stage, the Hausdorff distance and modified shape context are employed to measure and determine of similarity between models and test images. Our system is evaluated with experiments on the AR, ORL and Yale face database face images. From experimental result, it is show that the high accuracy rate.