Abstract

An image classifier is described in which recognition occurs by recursive interpretation of a hierarchy of symbolic images. Interpretation within any level is by direct matching with a limited memory that is hierarchically distributed. The memory is developed by learning. It is shown that this system conforms to the standard paradigm for low-level vision [ A. Rosenfeld, in Digest of the Topical Meeting on Machine Vision ( Optical Society of America, Washington, D.C., 1985)].

© 1986 Optical Society of America

Future directions in machine vision

Azriel Rosenfeld
J. Opt. Soc. Am. A 3(9) 1461-1464 (1986)

Rotation-invariant image recognition at low light levels

Thomas A. Isberg and G. Michael Morris
J. Opt. Soc. Am. A 3(7) 954-963 (1986)

Machine-vision techniques for inspection of printed wiring boards and thick-film circuits

Jorge L. C. Sanz and Anil K. Jain
J. Opt. Soc. Am. A 3(9) 1465-1482 (1986)

Three-dimensional object recognition from multiple views

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

Image classification at low light levels

Miles N. Wernick and G. Michael Morris
J. Opt. Soc. Am. A 3(12) 2179-2187 (1986)