Abstract

A procedure is presented for generating a small bank of optical correlation filters that can recognize a large number of perspective views of an object. The method applies to general kinds of image distortions in addition to those generated by different perspective views. The holographic filters are also invariant to image intensity and position (translation invariance). The method of design is to decompose the entire set of object variations into a set of eigenimages. These eigenimages contain complete information about the target set. An iterative procedure combines the eigenimages with different relative phases, so that complete target information can be extracted in an optical implementation. An example illustrates that a set of only 20 holographic filters recognizes a three-dimensional target over a continuous range of viewing angles.

© 1988 Optical Society of America

Three-dimensional object recognition from multiple views

R. Wu and H. Stark
J. Opt. Soc. Am. A 3(9) 1543-1557 (1986)

Experimental use of iteratively designed rotation invariant correlation filters

Donald W. Sweeney, Ellen Ochoa, and George F. Schils
Appl. Opt. 26(16) 3458-3465 (1987)

Iterative technique for the synthesis of optical-correlation filters

George F. Schils and Donald W. Sweeney
J. Opt. Soc. Am. A 3(9) 1433-1442 (1986)

Ill-posed problem of the constant-constraint criterion in optical correlation pattern recognition

Tao ChunKan
J. Opt. Soc. Am. A 12(10) 2114-2121 (1995)

Object recognition using three-dimensional optical quasi-correlation

Youzhi Li and Joseph Rosen
J. Opt. Soc. Am. A 19(9) 1755-1762 (2002)