DIRECTIONAL BINARY BARCODE FOR IMAGE RETRIEVAL

ELECTORONICS AND COMMUNICATION ENGINEERING

This paper proposes a novel scheme for image annotation. In recent years, advances in image processing lead to massive database in all the fields especially in medical field. Because of this an efficient abstraction and retrieval technique is necessary. The mainstay of this paper is to use directional binary algorithm for feature abstraction. Apart from retrieval and abstraction technique memory also plays a major role. Since number of images is more, storing it efficiently is necessary. Feature abstracted from images are converted into barcode and stored to save memory space. Retrieval technique used in this paper is hamming distance. To find the most discriminative Directional Binary barcode for a given query image, the effects of employing Directional binary algorithm with different parameters, i.e., different sets of scales and orientations, are investigated, resulting in different barcode lengths and retrieval performances.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.