Title :
Equal-average equal-variance nearest neighbor search algorithm based on Hadamard transform
Author :
Lu, Zhe-ming ; Pei, Hui
Author_Institution :
Dept. of Autom. Test & Control, Harbin Inst. of Technol., China
Abstract :
A new fast nearest neighbor codeword search algorithm for image vector quantization (VQ) is introduced. This algorithm uses two significant features of a hadamard transformed vector, that is, the average, the variance, to eliminate more unmatched code words. It saves a great deal of computational time and distortion calculations. Experimental results demonstrate the performance of the proposed algorithm is good.
Keywords :
Hadamard transforms; computational complexity; distortion; image coding; search problems; vector quantisation; EENNS; Hadamard transform; computational complexity; computational time; distortion calculation; equal average equal variance nearest neighbor search algorithm; image vector quantization; unmatched code words; Automatic control; Automatic testing; Distortion measurement; Electronic mail; Error correction; Error correction codes; Image coding; Nearest neighbor searches; Speech coding; Vector quantization;
Conference_Titel :
Machine Learning and Cybernetics, 2003 International Conference on
Print_ISBN :
0-7803-8131-9
DOI :
10.1109/ICMLC.2003.1260084
