Object detection with a nearest-neighbor classifier based on residual vector quantization

摘要

Abstract: The use of residual (multiple stage) vector quantizer codevectors in a nearest neighbor classifier for direct classification of image pixel data is proposed. This approach combines the successive approximation process generated by the residual vector quantizer with sequential decision making. This approach potentially has the advantage of making large data base searches for small object or texture recognition in images both computation and memory efficient. !8