Sciweavers

810 search results - page 43 / 162
» Learning to Segment Document Images
Sort
View
CORR
2011
Springer
222views Education» more  CORR 2011»
14 years 3 months ago
Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs
Abstract. We propose an extension of the Restricted Boltzmann Machine (RBM) that allows the joint shape and appearance of foreground objects in cluttered images to be modeled indep...
Nicolas Heess, Nicolas Le Roux, John M. Winn
ICDAR
2009
IEEE
14 years 9 months ago
Restoration and Segmentation of Highly Degraded Characters Using a Shape-Independent Level Set Approach and Multi-level Classifi
Segmentation of ancient documents is challenging. In the worst cases, text characters become fragmented as the results of strong degradation processes. New active contour methods ...
Reza Farrahi Moghaddam, David Rivest-Hénaul...
ICIP
2007
IEEE
16 years 1 months ago
A Case-Based Reasoning Approach for Unknown Class Invoice Processing
This paper introduces an invoice analysis approach using CaseBased Reasoning (CBR). CBR is used to analyze and interpret new invoices thanks to the previous processing experiences...
Abdel Belaïd, Hatem Hamza, Yolande Belaï...
ICDAR
2003
IEEE
15 years 5 months ago
Mirror Image Learning for Autoassociative Neural Networks
This paper studies on the mirror image learning algorithm for the autoassociative neural networks and evaluates the performance by handwritten numeral recognition test. Each of th...
Shusaku Shimizu, Wataru Ohyama, Tetsushi Wakabayas...
ICIP
2008
IEEE
16 years 1 months ago
Supervised methods for perfect segmentation in medical images
We pose the problem of perfect segmentation for regions with ambiguous boundaries. We design machine learning classifiers to identify boundaries and build these into an interactiv...
Tony Shepherd, Daniel C. Alexander