22 October 2001 ATR applications of minimax entropy models of texture and shape
Author Affiliations +
Abstract
Concepts from information theory have recently found favor in both the mainstream computer vision community and the military automatic target recognition community. In the computer vision literature, the principles of minimax entropy learning theory have been used to generate rich probabilitistic models of texture and shape. In addition, the method of types and large deviation theory has permitted the difficulty of various texture and shape recognition tasks to be characterized by 'order parameters' that determine how fundamentally vexing a task is, independent of the particular algorithm used. These information-theoretic techniques have been demonstrated using traditional visual imagery in applications such as simulating cheetah skin textures and such as finding roads in aerial imagery. We discuss their application to problems in the specific application domain of automatic target recognition using infrared imagery. We also review recent theoretical and algorithmic developments which permit learning minimax entropy texture models for infrared textures in reasonable timeframes.
© (2001) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Song-Chun Zhu, Alan L. Yuille, Aaron D. Lanterman, "ATR applications of minimax entropy models of texture and shape", Proc. SPIE 4379, Automatic Target Recognition XI, (22 October 2001); doi: 10.1117/12.445408; https://doi.org/10.1117/12.445408
PROCEEDINGS
10 PAGES


SHARE
Back to Top