Title :
Modular wavelet-based vector quantization for automatic target recognition
Author :
Chan, Lipchen Alex ; Nasrabadi, Nasser M.
Author_Institution :
Dept. of Electr. & Comput. Eng., State Univ. of New York, Buffalo, NY, USA
Abstract :
An automatic target recognition (ATR) classifier is constructed that uses a set of dedicated vector quantizers (VQs). The background pixels in each input image are properly clipped out by a set of aspect windows. The extracted target area for each aspect window is then enlarged to a fixed size, after which a wavelet decomposition splits the enlarged extraction into several subbands A dedicated VQ codebook is generated for each subband of a particular target class at a specific range of aspects. Thus, each codebook consists of a set of feature templates that are iteratively adapted to represent a particular subband of a given target class at a specific range of aspects. These templates are then further trained by a modified learning vector quantization (LVQ) algorithm that enhances their discriminatory characteristics. Finally, a path selector is designed to speed up the recognition process with a tolerable degradation in recognition rate
Keywords :
image classification; object recognition; vector quantisation; wavelet transforms; VQ codebook; automatic target recognition; dedicated vector quantizers; discriminatory characteristics; modified learning vector quantization algorithm; modular wavelet-based vector quantization; path selector; recognition process; wavelet decomposition; Degradation; Humans; Infrared image sensors; Iterative algorithms; Neural networks; Pixel; Real time systems; Surveillance; Target recognition; Vector quantization;
Conference_Titel :
Multisensor Fusion and Integration for Intelligent Systems, 1996. IEEE/SICE/RSJ International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3700-X
DOI :
10.1109/MFI.1996.572218