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 probabilistic 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.
ATR applications of minimax entropy models of texture and shape
2001
10 Seiten, 40 Quellen
Aufsatz (Konferenz)
Englisch
Learning Inhomogeneous Gibbs Model of Faces by Minimax Entropy
British Library Conference Proceedings | 2001
|MetaMorphs: Deformable Shape and Texture Models
British Library Conference Proceedings | 2004
|MetaMorphs: Deformable shape and texture models
IEEE | 2004
|Face alignment using texture-constrained active shape models
British Library Online Contents | 2003
|