Sciweavers

566 search results - page 55 / 114
» OCR with No Shape Training
Sort
View
JMIV
2007
143views more  JMIV 2007»
14 years 9 months ago
Measures for Benchmarking of Automatic Correspondence Algorithms
Automatic localisation of correspondences for the construction of Statistical Shape Models from examples has been the focus of intense research during the last decade. Several alg...
Anders Ericsson, Johan Karlsson
NN
2002
Springer
161views Neural Networks» more  NN 2002»
14 years 9 months ago
AANN: an alternative to GMM for pattern recognition
The objective in any pattern recognition problem is to capture the characteristics common to each class from feature vectors of the training data. While Gaussian mixture models ap...
B. Yegnanarayana, S. P. Kishore
CVPR
2005
IEEE
15 years 12 months ago
A Statistical Field Model for Pedestrian Detection
This paper presents a new statistical model for detecting and tracking deformable objects such as pedestrians, where large shape variations induced by local shape deformation can ...
Ying Wu, Ting Yu, Gang Hua
GISCIENCE
2010
Springer
244views GIS» more  GISCIENCE 2010»
14 years 11 months ago
Detecting Road Intersections from GPS Traces
As an alternative to expensive road surveys, we are working toward a method to infer the road network from GPS data logged from regular vehicles. One of the most important componen...
Alireza Fathi, John Krumm
ECCV
2004
Springer
15 years 11 months ago
A Linguistic Feature Vector for the Visual Interpretation of Sign Language
Abstract. This paper presents a novel approach to sign language recognition that provides extremely high classification rates on minimal training data. Key to this approach is a 2 ...
Richard Bowden, David Windridge, Timor Kadir, Andr...