Abstract
It is widely recognized that effective image processing and machine vision must involve the use of information at multiple scales, and that models of human vision must be multi-scale as well. The most commonly used image representations are linear transforms, in which an image is decomposed into a sum of elementary basis functions. Besides being well understood, linear transformations in the form of convolutions provide a useful model of some of the early processing in the human visual system.
© 1989 Optical Society of America
PDF ArticleMore Like This
Edward H. Adelson and Eero Simoncelli
WL6 OSA Annual Meeting (FIO) 1987
Eero Simoncelli, Edward H. Adelson, and Rajesh Hingorani
WL7 OSA Annual Meeting (FIO) 1987
Cheng-Yen Chien, Meng-Hsin Chen, Chia-Wei Pai, Yu-Jen Lee, Chiu-Chang Huang, Vin-Cent Su, and Chieh-Hsiung Kuan
STu3P.6 CLEO: Science and Innovations (CLEO:S&I) 2020