Keyblock for Content-based Image Retrieval (Vector quantization Comparison In Piercing Domain Image)

Abstract

Keyblock is a generalization of the text-based information retrieval technology in the image domain. The main purpose of this framework is to find the codebook of a given size from a set of training image blocks. This main purpose can be achieved with any Vector quantization algorithm. This paper is an answer to the questions: “Can we use keyblock for piercing pattern?” Which one is the best algorithm between GLA or PNNA for VQ ?” The paper begins by describing some basic theory of Texture Feature, Keyblock-based, Vector quantization, Generalized Lloyd Algorithm (GLA) and Pairwise Nearest Neighbour Algorithm (PNNA). Next, it summarizes the implementation of both algorithm in keyblock framework for piercing pattern. Finally, it describes the experimental result of this research.