SEPARATION OF TEXTURE AND SHAPE IN IMAGES OF FACES FOR IMAGE-CODING AND SYNTHESIS

Human faces differ in shape and texture. Image representations based o n this separation of shape and texture information have been reported by several authors [for a review, see Science 272, 1905 (1996)]. We in vestigate such a representation of human faces based on a separation o f texture and two-dimensional shape information. Texture and shape wer e separated by use of pixel-by-pixel correspondence among the various images, which was established through algorithms known from optical fl ow computation. We demonstrate the improvement of the proposed represe ntation over well-established pixel-based techniques in terms of codin g efficiency and in terms of the ability to generalize to new images o f faces. The evaluation is performed by calculating different distance measures between the original image and its reconstruction and by mea suring the time that human subjects need to discriminate them. (C) 199 7 Optical Society of America.