Sciweavers

7413 search results - page 195 / 1483
» Using Specularities for Recognition
Sort
View
CVPR
2007
IEEE
15 years 11 months ago
Visual Event Recognition in News Video using Kernel Methods with Multi-Level Temporal Alignment
In this work, we systematically study the problem of visual event recognition in unconstrained news video sequences. We adopt the discriminative kernel-based method for which vide...
Dong Xu, Shih-Fu Chang
MVA
2002
125views Computer Vision» more  MVA 2002»
15 years 4 months ago
Recognition of 3-D Free-form Objects Using Distance-supported Shape Index
In this paper, we present an approach to incorporating partial geometric information into a local feature-based The distance-supported shape index is proposed for the representatio...
Dong-O Kim, Sang Wook Lee, Rae-Hong Park
ICPR
2008
IEEE
15 years 11 months ago
Novel image feature alphabets for object recognition
Most successful object recognition systems are based on a visual alphabet of quantised gradient orientations. Here, we introduce two richer image feature alphabets for use in obje...
Martin Lillholm, Lewis D. Griffin
EP
1998
Springer
15 years 9 months ago
A DTD Extension for Document Structure Recognition
This paper deals with the representation of document models used in the field of document recognition. A novel formalism called generalized n-gram is presented, which is shown to b...
Rolf Brugger, Frédéric Bapst, Rolf I...
MVA
1990
101views Computer Vision» more  MVA 1990»
15 years 5 months ago
A Segmentation Free Approach to Symbol Extraction and Recognition from Image Document
: We present a symbol recognition method without segmentation of the document. Our approach uses Zernike moments for the coding and a multilayered Perceptron for the classifier. Re...
Maurice Milgram, Mattieu Jobert, Bertrand Lamy