Abstract. We develop an object detection method combining top-down recognition with bottom-up image segmentation. There are two main steps in this method: a hypothesis generation s...
Abstract. In this paper, we present a deformable-model based solution for segmenting objects with complex texture patterns of all scales. The external image forces in traditional d...
Xiaolei Huang, Zhen Qian, Rui Huang, Dimitris N. M...
A robust segmentation is the most important part of an automatic character recognition system (e.g. document processing, license plate recognition etc.). In our contribution we pr...
Global shape information is an effective top-down complement
to bottom-up figure-ground segmentation as well
as a useful constraint to avoid drift during adaptive tracking.
We p...
Text line segmentation in unconstrained handwritten documents remains a challenge because handwritten text lines are multi-skewed and not obviously separated. This paper presents ...