Share Email Print

Proceedings Paper

Evolution of convolution kernels for feature extraction
Author(s): Shawn C. Masters; Kenneth J. Hintz
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A fundamental difficulty in image processing is the determination of a suitable set of features which can be used to segment images or can be combined by an appropriate method for the identification and classification of targets. Many features have been and are being used which are `reasonable' to the target recognition researcher, but there is no assurance that other features which can extract more information from an image don't exist. This paper investigates the use of genetic algorithms (GA) to evolve convolution kernels which produce features that can be used for image segmentation. Any linear transform can be implemented as a convolution kernel. Using supervised learning and a fitness function which maximizes the interclass distance and minimizes intraclass variance, a genetic algorithm is used to evolve a sub-image convolution kernel. The genome which represents the convolution kernel is converted from a 2-D form into a 1-D form using an approach similar to a space-filling curve. The fitness of the genome for each kernel is measured by its classification performance compared to ground truth data, and then biased by the size of the kernel so that a smallest kernel solution can be found.

Paper Details

Date Published: 5 July 1995
PDF: 9 pages
Proc. SPIE 2484, Signal Processing, Sensor Fusion, and Target Recognition IV, (5 July 1995); doi: 10.1117/12.213047
Show Author Affiliations
Shawn C. Masters, George Mason Univ. (United States)
Kenneth J. Hintz, George Mason Univ. (United States)

Published in SPIE Proceedings Vol. 2484:
Signal Processing, Sensor Fusion, and Target Recognition IV
Ivan Kadar; Vibeke Libby, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?