Global motion is estimated either in the pixel domain or in block based domain. Until now, all the approaches regarding the latter are based on fixed sized blocks while the recent...
Marina Georgia Arvanitidou, Alexander Glantz, Andr...
We present a novel algorithm for unsupervised segmentation of natural images that harnesses the principle of minimum description length (MDL). Our method is based on observations ...
Shankar Rao, Hossein Mobahi, Allen Y. Yang, Shanka...
This paper presents a robust and efficient skeleton-based graph matching method for object recognition and recovery applications. The novel feature is to unify both object recogni...
Kernel descriptors provide a unified way to generate rich visual feature sets by turning pixel attributes into patch-level features, and yield impressive results on many object rec...
Liefeng Bo, Kevin Lai, Xiaofeng Ren and Dieter Fox
Object recognition can be formulated as matching image features to model features. When recognition is exemplar-based, feature correspondence is one-to-one. However, segmentation e...
M. Fatih Demirci, Ali Shokoufandeh, Yakov Keselman...