Interactive browsing of image repositories
ICCVG'12 Proceedings of the 2012 international conference on Computer Vision and Graphics
| Hi-index | 0.00 |
This paper presents a new approach for Content-Based Image Retrieval (CBIR) using Virtual Reality (VR) technology. In this paper, VR is used for sorting and visualizing image databases in a 3D virtual environment and for representing the results of the search. After reviewing the state-of-the-art of color image retrieval, the paper introduces the techniques of feature extraction, filtering, feature fusion, image browsing and navigation, and their implications for VR-based color image retrieval. Although high level semantic processing is often necessary to produce useful navigation aids and search techniques, we apply low level color, texture and shapes features for our color image discrimination associating content with other multimedia information such as image titles (text) due to effective implementation. Our feature fusion based on Weighted Multidimensional Scaling (WMDS) has added to the existing techniques. Based on this experimental investigation using a color-texture database, we have shown that virtual reality offers significant advantages as a tool for image retrieval.