Paper data
Title:
Vector Quantization Fast Search Algorithm using Hyperplane Based kdimensional Multinode Search Tree Author(s): Chan KamFai, HKUST Woo KamTim, HKUST Kok ChiWah, HKUST Page numbers in the proceedings: Volume I pp 265268 Session: Source Coding
Paper abstract
A vector quantization fast search algorithm using hyperplane based kdimensional multinode search tree is presented. Misclassification problem associated with hyperplane decision is eliminated by a multilevel backtracing algorithm. The vector quantization complexity is further lowered by a novel relative distance quantization rule. Triangular inequality is applied to lower bound the search distance, thus eliminated all the subtree in the kdimensional search tree during backtracing. Vector quantization image coding results are presented which showed the proposed algorithm outperform other algorithms in literature both in PSNR and computation time.
Paper
