An Alignment-free Approach for Image Matching Applications

Alignment of images plays an important role in computer vision applications such as image registration and image matching applications. In image registration applications, alignment brings similar points of images into correspondence, whereas in image matching applications alignment acts as an intermediate step and it helps in assessing the similarity between two images. For higher accuracy and efficiency, this thesis has proposed a new transform based alignment approach for registering images and an alignment-free approach the can match images without explicitly extracting image features. Furthermore, the proposed method is application independent and applicable to both full and partial images.