Year: 2005
Type: article
Abstract: The encoding of vector quantization (VQ) needs expensive computation for searching the closet codeword to the input vectors. In order to reduce computational burden, many researchers have developed some efficient full-search-equivalent algorithm by using the characteristics of the means and variances of a vector. However, some computational redundancies still exist in them. In this paper, we introduce a technique to efficiently partition a vector into two dynamic subvectors according to the patterns inside the block (or vector) and then further improve the computational load. Experimental results show that the proposed method provides a higher codeword searching efficiency than other existing algorithms.
Source: IEICE Electronics Express
DOI: 10.1587/elex.2.458
Authors: Chou-Chen Wang, Chi-Wei Tung
Institution: I-Shou University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W2091884468