Sciweavers

664 search results - page 98 / 133
» Unsupervised Category Modeling, Recognition, and Segmentatio...
Sort
View
NECO
2007
127views more  NECO 2007»
13 years 8 months ago
Visual Recognition and Inference Using Dynamic Overcomplete Sparse Learning
We present a hierarchical architecture and learning algorithm for visual recognition and other visual inference tasks such as imagination, reconstruction of occluded images, and e...
Joseph F. Murray, Kenneth Kreutz-Delgado
CIVR
2010
Springer
235views Image Analysis» more  CIVR 2010»
13 years 7 months ago
Dynamic textures for human movement recognition
Human motion can be seen as a type of texture pattern. In this paper, we adopt the ideas of spatiotemporal analysis and the use of local features for motion description. movements...
Vili Kellokumpu, Guoying Zhao, Matti Pietikäi...
ICDAR
2009
IEEE
13 years 6 months ago
Learning on the Fly: Font-Free Approaches to Difficult OCR Problems
Despite ubiquitous claims that optical character recognition (OCR) is a "solved problem," many categories of documents continue to break modern OCR software such as docu...
Andrew Kae, Erik G. Learned-Miller
CVIU
2006
166views more  CVIU 2006»
13 years 8 months ago
Non-parametric and light-field deformable models
Statistical shape-and-texture appearance models use image morphing to define a rich, compact representation of object appearance. They are useful in a variety of applications incl...
Chris Mario Christoudias, Louis-Philippe Morency, ...
SCVMA
2004
Springer
14 years 2 months ago
2D Motion Description and Contextual Motion Analysis: Issues and New Models
Abstract. In this paper, several important issues related to visual motion analysis are addressed with a focus on the type of motion information to be estimated and the way context...
Patrick Bouthemy