Image Matching method using Hierarchical Clustering of Deformable-objects

초록

Image matching is a fundamental method for computer vision such as object detection, visual tracking, image recognition and augmented reality. Recently, the new challenge is image matching of deformable-objects. Deformable image matching is matched similar images or objects in image, even under geometric, affine and complex transformations. In the real world, deformable- object images encompass the majority of all objects. However, since deformable-object image matching has a different target than the existing image matching methods, feature detection and matching methods are not identical. As such, much research has been conducted into achieving both objectives at the same time, but without substantial results. This paper proposed the method that deformable-objects images matching using feature points and hierarchical clustering of matching pairs.