Content Based Image Retrieval System Using NOHIS-tree

TL;DR

This paper introduces NOHIS-Search, a content-based image retrieval system utilizing NOHIS-tree indexing, which outperforms existing systems using PDDP and sequential search in large image databases.

Contribution

The paper presents a novel CBIR system based on NOHIS-tree indexing, demonstrating improved performance over existing methods.

Findings

NOHIS-Search outperforms PDDP-based CBIR systems.

NOHIS-Search outperforms sequential search methods.

System tested on ImagEval database with positive results.

Abstract

Content-based image retrieval (CBIR) has been one of the most important research areas in computer vision. It is a widely used method for searching images in huge databases. In this paper we present a CBIR system called NOHIS-Search. The system is based on the indexing technique NOHIS-tree. The two phases of the system are described and the performance of the system is illustrated with the image database ImagEval. NOHIS-Search system was compared to other two CBIR systems; the first that using PDDP indexing algorithm and the second system is that using the sequential search. Results show that NOHIS-Search system outperforms the two other systems.