Sciweavers

1133 search results - page 165 / 227
» Extraction of semantic objects from still images
Sort
View
ICPR
2000
IEEE
14 years 10 months ago
Detecting Rotational Symmetries Using Normalized Convolution
Perceptual experiments indicate that corners and curvature are very important features in the process of recognition. This paper presents a new method to detect rotational symmetr...
Björn Johansson, Gösta H. Granlund, Hans...
DAGM
2005
Springer
14 years 2 months ago
6D-Vision: Fusion of Stereo and Motion for Robust Environment Perception
Obstacle avoidance is one of the most important challenges for mobile robots as well as future vision based driver assistance systems. This task requires a precise extraction of de...
Uwe Franke, Clemens Rabe, Hernán Badino, St...
ICDAR
2003
IEEE
14 years 2 months ago
Analysis of Handwriting Individuality Using Word Features
Analysis of allographs (characters) and allograph combinations (words) is the key for obtaining the discriminating elements of handwriting. While allographs usually inhabit in wor...
Bin Zhang, Sargur N. Srihari
MIR
2010
ACM
232views Multimedia» more  MIR 2010»
14 years 3 months ago
Exploiting external knowledge to improve video retrieval
Most video retrieval systems are multimodal, commonly relying on textual information, low- and high-level semantic features extracted from query visual examples. In this work, we ...
David Vallet, Iván Cantador, Joemon M. Jose
CVPR
2012
IEEE
11 years 11 months ago
Action bank: A high-level representation of activity in video
Activity recognition in video is dominated by low- and mid-level features, and while demonstrably capable, by nature, these features carry little semantic meaning. Inspired by the...
Sreemanananth Sadanand, Jason J. Corso