AN EMPIRICAL STUDY OF QUERY EFFECTIVENESS IMPROVEMENT VIA MULTIPLE VISUAL FEATURE INTEGRATION

Abstract

This article is a comprehensive evaluation of a new framework for indexing image data, called CMVF, which can combine multiple data properties with a hybrid architecture. The goal of this system is to allow straightforward incorporation of multiple visual feature vectors, based on properties such as color, texture and shape, into a single low-dimension vector that is more effective for retrieval than the larger individual feature vectors. Moreover, CMVF is not only constrained to visual properties, but can also incorporate human classification criteria to further strengthen image retrieval process. The controlled study present in this paper concentrates on CMVF's performance on images, examining how the incorporation of extra features into the indexing affects both efficiency and effectiveness. Analysis and empirical evidence suggest that the inclusion of extra visual features can significantly improve system performance. Furthermore, it demonstrated that CMVF's effectiveness is robust against various kinds of common image distortions and initial (random) configuration of neural network.