Morphing Human Faces: Automatic Control Points Selection And Color Transition

In this paper, we propose a morphing method by which face color images can be freely transformed. The main focus of this work is the transformation of one face image to another. This method is fully automatic in that it can morph two face images by automatically detecting all the control points necessary to perform the morph. A face detection neural network, edge detection and medium filters are employed to detect the face position and features. Five control points, for both the source and target images, are then extracted based on the facial features. Triangulation method is then used to match and warp the source image to the target image using the control points. Finally color interpolation is done using a color Gaussian model that calculates the color for each particular frame depending on the number of frames used. A real coded Genetic algorithm is used in both the image warping and color blending steps to assist in step size decisions and speed up the morphing. This method results...

• Type: Conference
• Year: 2004
• Where: IJIT
• Authors: Stephen Karungaru, Minoru Fukumi, Norio Akamatsu
• Keywords: Artificial Intelligence, Control Points, Face Images, IJIT 2004, Image