SAM-based Image Indexing and Retrieval System using LAB Color Characteristics

摘要

A color-based image indexing technique that facilitates the image database search process is provided in this paper. Our indexing approach is based on a LAB color-based image feature extraction producing high-dimensional feature vectors that are accessed via Spatial Access Methods. These content-based feature vectors are indexed by using a K-D-tree structure. An efficient retrieval process, using a relevance-feedback scheme and performing a K-NN image search based on this indexing structure, is then described in this article.