English

An Affinity Propagation Based method for Vector Quantization Codebook Design

Computer Vision and Pattern Recognition 2007-10-11 v2

Abstract

In this paper, we firstly modify a parameter in affinity propagation (AP) to improve its convergence ability, and then, we apply it to vector quantization (VQ) codebook design problem. In order to improve the quality of the resulted codebook, we combine the improved AP (IAP) with the conventional LBG algorithm to generate an effective algorithm call IAP-LBG. According to the experimental results, the proposed method not only enhances the convergence abilities but also is capable of providing higher-quality codebooks than conventional LBG method.

Cite

@article{arxiv.0710.2037,
  title  = {An Affinity Propagation Based method for Vector Quantization Codebook Design},
  author = {Wu Jiang and Fei Ding and Qiao-liang Xiang},
  journal= {arXiv preprint arXiv:0710.2037},
  year   = {2007}
}

Comments

In this version we make some explaination about the network-support similarity

R2 v1 2026-06-21T09:29:49.871Z