15 March 1994 Efficient discrete Gabor functions for robot vision
Author Affiliations +
Abstract
A new discrete Gabor function provides subpixel resolution of phase while overcoming many of the computational burdens of current approaches to Gabor function implementation. Applications include hyperacuity measurement of binocular disparity and optic flow for stereo vision. Convolution is avoided by exploiting band-pass to subsample the image plane. A general purpose front end processor for robot vision, based on a wavelet interpretation of this discrete Gabor function, can be constructed by tessellating and pyramiding the elementary filter. Computational efficiency opens the door to real-time implementation which mimics many properties of the simple and complex cells in the visual cortex.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Carl F. R. Weiman, "Efficient discrete Gabor functions for robot vision", Proc. SPIE 2242, Wavelet Applications, (15 March 1994); doi: 10.1117/12.170019; https://doi.org/10.1117/12.170019
PROCEEDINGS
13 PAGES


SHARE
KEYWORDS
Image filtering

Phase measurement

Wavelets

Modulation

Bandpass filters

Gaussian filters

Image analysis

RELATED CONTENT


Back to Top