Automatic Design and Synthesis of Automatic Target Recognition (ATR) Systems Using Learning Paradigms
Abstract
This report investigates evolutionary computational techniques such as genetic programming (GP), coevolutionary genetic programming (CGP), linear genetic programming (LGP) and genetic algorithms (GA) to automate the synthesis and analysis of object detection and recognition systems. It shows the efficacy of evolutionary computation in synthesizing effective composite operators and composite features from domain-independent primitive image processing operations and primitive features for object detection and recognition. Smart crossover, smart mutation and a new fitness function based on minimum description length (MDL) principle are designed to improve the efficiency of genetic programming. A new MDL-based fitness function is proposed to improve the genetic algorithm s performance on feature selection for object detection and recognition. Results are shown using MSTAR SAR imagery.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 01, 2003
- Accession Number
- ADA424338
Entities
People
- Bir Bhanu
- Krzysztof Krawiec
- Yingqiang Lin
Organizations
- University of California, Riverside