抽象的

Image Matching Using Invariant Local Features

Swathi V Nair, Thamizharasi A

Feature extraction and Image matching are the important task in computer vision. Variations of view and illumination are the challenges in image matching process. There are many methods have been proposed presently in order to address these problems using invariant detectors and descriptors. Then also the matching performance is still unstable and inaccurate. Here propose a method that introduces a view and illumination invariant image-matching. And transform the view of one image to the other, and normalize their illumination for accurate matching. The proposed method is based on SURF based feature extraction.