Sciweavers

566 search results - page 73 / 114
» OCR with No Shape Training
Sort
View
IEEEICCI
2009
IEEE
14 years 7 months ago
Learning from an ensemble of Receptive Fields
Abstract-In this paper, we construct a neural-inspired computational model based on the representational capabilities of receptive fields. The proposed model, known as Shape Encodi...
Hanlin Goh, Joo Hwe Lim, Chai Quek
CVPR
2009
IEEE
16 years 5 months ago
Increased Discrimination in Level Set Methods with Embedded Conditional Random Fields
We propose a novel approach for improving level set seg- mentation methods by embedding the potential functions from a discriminatively trained conditional random field (CRF) in...
Dana Cobzas (University of Alberta), Mark Schmidt ...
CVPR
2007
IEEE
15 years 12 months ago
Multiple Class Segmentation Using A Unified Framework over Mean-Shift Patches
Object-based segmentation is a challenging topic. Most of the previous algorithms focused on segmenting a single or a small set of objects. In this paper, the multiple class objec...
Lin Yang, Peter Meer, David J. Foran
ICCV
2007
IEEE
15 years 12 months ago
Retrieving actions in movies
We address recognition and localization of human actions in realistic scenarios. In contrast to the previous work studying human actions in controlled settings, here we train and ...
Ivan Laptev, Patrick Pérez
ICIP
2005
IEEE
15 years 11 months ago
Optimised filters for texture defect detection
This paper presents a new approach to texture defect detection based on a set of optimised filters. Each filter is applied to one wavelet sub-band and its size and shape are tuned ...
João Luís Sobral