Object recognition forms a ubiquitous problem in digital image processing. The detection of robust image features of high distinctiveness is one important key in this regard. We p...
We present a general framework for image discrimination based on identifying small, localized differences between images. Our novel matching scheme is based on an alternate inform...
Huzefa Neemuchwala, Alfred O. Hero, Paul L. Carson...
There have been important recent advances in object recognition through the matching of invariant local image features. However, the existing approaches are based on matching to i...
This paper presents a semi-supervised learning (SSL) approach to find similarities of images using statistics of local matches. SSL algorithms are well known for leveraging a larg...
Image metamorphosis as an animation tool has mostly been employed in the context of the entire image. This work explores the use of isolated and focused image based metamorphosis ...