Fast nearest neighbor search of entropy-constrained vector quantization

Michael Hiroshi Johnson, Richard E. Ladner, E.A. Riskin · IEEE Transactions on Image Processing · 2000

Entropy-constrained vector quantization (ECVQ) offers substantially improved image quality over vector quantization (VQ) at the cost of additional encoding complexity. We extend results in the literature for fast nearest neighbor search of VQ to ECVQ. We use a new, easily computed distance that successfully eliminates most codewords from consideration.

Read the paper · More papers on PaperTik