Set Enumeration Tree based Image Representation for Gray Level Image Storage and Retrieval

Abstract

The recent growth of communications and multimedia applications had led to the requirement of mass storage space as well as efficient retrieval technique especially for multimedia data. In this paper, a novel approach for representing gray level image for data storage and image retrieval is proposed. The proposed approach used set enumeration tree data structures where only unique image pattern is stored in the image data structure. The overall structure involves two types of tree data structures; the first tree is low-level image pattern tree to store the unique gray level image pattern and the second tree is used to store the image path by referring to the first tree data structure. The low-level image pattern tree is predefined and will not expand throughout the image encoding process. The size of the second tree is gradually expanded as the result of addition of new image path during image encoding. Through unique image pattern encoding into a tree, there will be no redundant image features, thus leading to saving storing space. Caltech-101 gray level image datasets were used to test the proposed approach and the results showed that it could lead to saving storage space while provide promising performance in image retrieval.