Sciweavers

61 search results - page 10 / 13
» Combining Alignment Results for Historical Handwritten Docum...
Sort
View
ICDAR
2007
IEEE
15 years 9 months ago
On the Use of Lexeme Features for Writer Verification
Document examiners use a variety of features to analyze a given handwritten document for writer verification. The challenge in the automatic classification of a pair of documents ...
A. Bhardwaj, A. Singh, Harish Srinivasan, Sargur N...
ICDAR
2009
IEEE
15 years 3 months ago
A Feedback-Based Multi-Classifier System
Multi-classifier approach is a widespread strategy used in many difficult classification problems. Traditionally, in a multi-classifier approach, a classification decision based o...
Giuseppe Pirlo, Claudia Adamita Trullo, Donato Imp...
ICDAR
2009
IEEE
15 years 3 months ago
Evaluation of Different Strategies to Optimize an HMM-Based Character Recognition System
Different strategies for combination of complementary features in an HMM-based method for handwritten character recognition are evaluated. In addition, a noise reduction method is...
Murilo Santos, Albert Hung-Ren Ko, Luiz S. Oliveir...
ICDAR
2007
IEEE
16 years 8 days ago
A Bayesian Network Approach to Mode Detection for Interactive Maps
This paper describes a mode detection system for online pen input that employs a Bayesian network to combine classification results and context information. Previous monolithic c...
Don Willems, Louis Vuurpijl
ICDAR
2003
IEEE
15 years 11 months ago
Comparison of Genetic Algorithm and Sequential Search Methods for Classifier Subset Selection
Classifier subset selection (CSS) from a large ensemble is an effective way to design multiple classifier systems (MCSs). Given a validation dataset and a selection criterion, the...
Hongwei Hao, Cheng-Lin Liu, Hiroshi Sako