An efficient image retrieval framework using fused information feature

The tremendous growth in the number of digital images has provoked the need for improvement in search and retrieval of images from a large database. The biggest challenge faced in this process is retrieval of the required images from a large database with maximum precision and minimum retrieval time. Selecting appropriate features plays a significant role in improving the performance of image retrieval systems. In this paper, Fused Information Feature-based Image Retrieval System (FIF-IRS) is proposed, consisting of 8-Directional Gray Level Co-occurrence Matrix (8D-GLCM) and HSV Color Moments (HSVCM) features. The performance of the image retrieval system is evaluated by the metrics Precision, Error Rate, and Retrieval Time. The proposed image retrieval system is tested on benchmark image databases- Corel-1K, Corel-5K, and Corel-10K. The experimental results obtained prove that there is a significant improvement while applying the proposed method when compared to existing state-of-the-art techniques with attained precision of 83.3%, 66.9%, and 56.4% on the three databases respectively.