In this paper, we propose a general framework for fusing bottom-up segmentation with top-down object behavior classification over an image sequence. This approach is beneficial fo...
: 2D Face images are traditionally used in civil governmental applications. An extension from 2D to 3D images will lead to several advantages when setting up automated authenticati...
Xuebing Zhou, Tom A. M. Kevenaar, Emile Kelkboom, ...
The purpose of this paper is to develop a motionbased segmentation for digital image sequences that is based on continuous wavelet transform. Continuous wavelet transform allows e...
Mingqi Kong, Jean-Pierre Leduc, Bijoy K. Ghosh, M....
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....
Abstract. Recently, there has been increasing interests in applying aspect models (e.g., PLSA and LDA) in image segmentation. However, these models ignore spatial relationships amo...