Culminating Project Title
Date of Award
Culminating Project Type
Computer Science: M.S.
Computer Science and Information Technology
School of Science and Engineering
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Keywords and Subject Headings
Content Based Image Retrieval, CBIR, Image Comparison, Color Histogram, Image Retrieval, Image Processing
Content Based Image Retrieval (CBIR) is still a major research area due to its complexity and the growth of the image databases. Color Based Image Retrieval is one of the major retrieval methods in Content Based Image Retrieval systems. At present, researchers combine image retrieval techniques to get more accurate results. With the large image databases, image retrieval is still a challenging area and the efficiency of the image retrieval techniques still need to be considered. For this purpose, a comparative study of image retrieval techniques has been discussed in this paper. In addition, an efficient method is presented which aids to retrieve images by storing an intermediate result of the process in the database. To compare the query image and the images in the database, Euclidean distance, Normalized Cross Correlation distance and Histogram Intersection distance are taken as distance measures. Experimental results demonstrate Histogram Intersection distance is better than the other two methods. The intermediate result was stored using an event in the system. By making minor modifications to the proposed system, it creates a possibility for the user to add images to the database just by clicking on a button. Thus, the user can expand his/her database on his/her own will. Results show a significant improvement of performance in the proposed method.
Ranasinghe Arachchilage, Ishan P. Mr., "Building an Efficient Content Based Image Retrieval System by Changing the Database Structure" (2016). Culminating Projects in Computer Science and Information Technology. 15.