Association Rule Based Mining Approach for Building and Querying Map Image Databases using Correlation Analysis

Estimating geographic information from an image is an excellent, difficult high-level computer vision problem whose time has come. The emergence of vast amounts of geographically calibrated image data is a great reason for computer vision to start looking globally on the scale of the entire planet. In this paper, we propose a correlated association rule based framework for querying an image database The analysis is based on geographic locations from a single image using a purely data driven feature extraction approach. We apply a specific set of traditional data mining techniques such as association to the non traditional domain of image datasets. Image Features are selected based on the position of the image objects using color histograms approach and Line features. Correlation analysis is applied on image datasets using association rule. A query model based on Query by Example (QBE) is proposed. And we improve the technique further by using association rule based query mining.