A work minimization approach to image morphing

We present an algorithm for morphing two images, often with little or no us er interaction. For two similar images (such as different faces against a n eutral background), the algorithm generally can create a pleasing morph com pletely automatically. The algorithm seeks to minimize the work needed to d eform one image into the other. Work is defined as a function of the amount of warping and recoloration. We invoke a hierarchical method for finding a minimal work solution. Anchor point constraints are satisfied by penalties imposed on deformations that disobey these constraints. Good results can b e obtained in less than 10 s for 256x256 images.