Real-time face blending by automatic facial feature point detection

Abstract

We propose a real-time ldquoface blendingrdquo method based on an automatic detection of facial feature points. The method can blend faces of two or more people and generate a morphing-like synthetic image. The proposed method is able to create natural blended images fast. First, fourteen types of facial feature points are detected automatically in both base and texture images. Then the correspondences of the feature points and those of a 3D generic facial shape model are calculated for both images. An intermediate image whose corresponding coordinates for the model are known is generated from the texture image. Finally the blended image is rendered using the generated intermediate image and the base image. The effectiveness of the proposed method is shown through experimental results.