Abstract

The Hough transform is a powerful feature extraction algorithm transforming parametric curves of objects into a smaller feature space called the parameter domain. Optical implementation of the Hough transform by space-variant holographic filters is discussed, and a computer controlled system for generating such filters is described. Employing this system, filters for images of space bandwidth product of 60 × 60 are generated and applied to recognize and detect straight lines and circles in parallel and real time.

© 1986 Optical Society of America

Optical Hough-transform processor with a two-dimensional array of computer-generated holograms

Kunihiko Mori and Ryoji Ohba
Appl. Opt. 33(14) 3111-3117 (1994)

Optical implementation of the hough transform by use of rotationally multiplexed holograms

Dong-Hak Shin and Ju-Seog Jang
Appl. Opt. 37(2) 329-333 (1998)

Optical Hough transform

William H. Steier and Raj K. Shori
Appl. Opt. 25(16) 2734-2738 (1986)

High-speed acousto-optic mapping modulator for the generalized Hough transform

David Casasent and Jeffrey Richards
Appl. Opt. 32(35) 7217-7224 (1993)

Coherent optical production of the Hough transform

George Eichmann and B. Z. Dong
Appl. Opt. 22(6) 830-834 (1983)