Automatic Target Recognition Using Wavelet-Based Vector Quantization
Lipchen Alex Chan, Nasser M. Nasrabadi · 1997
Abstract : An automatic target recognition classifier is described that uses a set of dedicated vector quantizers (VQs) in the wavelet domain. 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 is used to split this region into several subbands. A dedicated VQ codebook is then 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 was designed to speed up the recognition process at the expense of a tolerable degradation in the recognition rate.