Sciweavers

904 search results - page 106 / 181
» Object Recognition by Integrating Multiple Image Segmentatio...
Sort
View
KAIS
2006
172views more  KAIS 2006»
13 years 7 months ago
CoMMA: a framework for integrated multimedia mining using multi-relational associations
Generating captions or annotations automatically for still images is a challenging task. Traditionally, techniques involving higher-level (semantic) object detection and complex f...
Ankur Teredesai, Muhammad A. Ahmad, Juveria Kanodi...
CVPR
2007
IEEE
14 years 9 months ago
Learning and Matching Line Aspects for Articulated Objects
Traditional aspect graphs are topology-based and are impractical for articulated objects. In this work we learn a small number of aspects, or prototypical views, from video data. ...
Xiaofeng Ren
PCM
2004
Springer
326views Multimedia» more  PCM 2004»
14 years 1 months ago
Automatic Video Object Tracking Using a Mosaic-Based Background
In this paper, we propose a panorama-based object tracking scheme for wide-view surveillance systems that can detect and track moving objects with a pan-tilt camera. A dynamic mosa...
Young-Kee Jung, Kyu-Won Lee, Dong-Min Woo, Yo-Sung...
TSMC
2008
138views more  TSMC 2008»
13 years 7 months ago
Image Thresholding Using Graph Cuts
A novel thresholding algorithm is presented in this paper to improve image segmentation performance at a low computational cost. The proposed algorithm uses a normalized graphcut m...
Wenbing Tao, Hai Jin, Yimin Zhang, Liman Liu, Desh...
PR
2007
126views more  PR 2007»
13 years 7 months ago
Convex hull based skew estimation
Skew estimation and page segmentation are the two closely related processing stages for document image analysis. Skew estimation needs proper page segmentation, especially for doc...
Bo Yuan, Chew Lim Tan