There is a significant need to extract and analyse the text in images on Web documents, for effective indexing, semantic analysis and even presentation by non-visual means (e.g....
In this paper we explore the problem of accurately segmenting a person from a video given only approximate location of that person. Unlike previous work which assumes that the app...
A motion-based, correspondence-free technique for human gait recognition in monocular video is presented. We contend that the planar dynamics of a walking person are encoded in a ...
We present a novel framework for tree-structure embedded density estimation and its fast approximation for mode seeking. The proposed method could find diverse applications in co...
We propose a new multiphase level set framework for image segmentation using the Mumford and Shah model, for piecewise constant and piecewise smooth optimal approximations. The pro...