Abstract

Human faces differ in shape and texture. Image representations based on this separation of shape and texture information have been reported by several authors [for a review, see Science 272, 1905 (1996)]. We investigate such a representation of human faces based on a separation of texture and two-dimensional shape information. Texture and shape were separated by use of pixel-by-pixel correspondence among the various images, which was established through algorithms known from optical flow computation. We demonstrate the improvement of the proposed representation over well-established pixel-based techniques in terms of coding efficiency and in terms of the ability to generalize to new images of faces. The evaluation is performed by calculating different distance measures between the original image and its reconstruction and by measuring the time that human subjects need to discriminate them.

© 1997 Optical Society of America

Discriminant analysis for recognition of human face images

Kamran Etemad and Rama Chellappa
J. Opt. Soc. Am. A 14(8) 1724-1733 (1997)

Low-dimensional representation of faces in higher dimensions of the face space

A. J. O’Toole, H. Abdi, K. A. Deffenbacher, and D. Valentin
J. Opt. Soc. Am. A 10(3) 405-411 (1993)

3D shape recovery algorithm from image orientations of textured surfaces

Takeaki Shimokawa
J. Opt. Soc. Am. A 40(9) 1673-1679 (2023)

Application of partial modeling techniques for texture segmentation

Dragana Carević and Terry Caelli
J. Opt. Soc. Am. A 14(11) 2924-2937 (1997)

Characterization of the spatial-frequency spectrum in the perception of shape from texture

Ko Sakai and Leif H. Finkel
J. Opt. Soc. Am. A 12(6) 1208-1224 (1995)