Абстрактный

Retrieval of Geographic Images Using Multi Support Vector Machine and Local Invariant Features

S.Radha , A.S. Rehna

This paper deals with retrieval of geographic images. For the retrieval of geographic images it uses local invariant features. SIFT algorithm is used. Multi SVM algorithm is used to perform image retrieval and using this algorithm the false image retrieval is considerably reduced. An SVM training algorithm builds a model that assigns new examples into one category or the other, making it a non-probabilistic binary linear classifier. Local features allows a greater range of objects and spatial patterns to be observed. SIFT detector is used to identify the key-points in the image. Feature extraction is used to extract features from the image. Using the proposed algorithm the image retrieval is shown to give accurate results. It not only performs image retrieval but also detection and classification of geographic images.