Abstract
In this paper we present a novel approach to match two images in presenting large scale and rotation changes. The proposed approach is based on scale invariant region description. Scale invariant region is detected by a two-step process and represented by a new descriptor. The descriptor is a two-dimensional gray-level histogram. Different descriptors can be directly compared. In addition, our descriptor is invariant to image rotation and large scale changes as well as robust to small viewpoint changes. The experiments demonstrate that our method is effective enough for image matching and retrieval.
Full Text
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call