Geographic Image Retrieval Using Local Invariant Features with Euclidean Distance

An image retrieval system is a computer system for browsing, searching and retrieving images from a large database of digital images. A robust natural and geographic image retrieval using a supervised classifier which concentrates on extracted features is proposed. Gray level cooccurrence matrix (GLCM), Scale invariant feature technique(SIFT) and moment invariant features are implemented to extract the features from natural images. Then these features are passed through SVM classifier. SVM classifies whether the input is Geographic or natural image. Based on the SVM result, the retrieval process is done with Euclidean distance. The performance comparison is done with standard features such as colour and texture. KeywordsGLCM, moment invariant, SIFT, SVM.