This paper investigates various ensemble methods for offline handwritten text line recognition. To add handwritten notes on pdf ensembles of recognisers, we implement bagging, random feature subspace, and language model variation methods.
For the combination, the word sequences returned by the individual ensemble members are first aligned. Then a confidence-based voting strategy determines the final word sequence. A number of confidence measures based on normalised likelihoods and alternative candidates are evaluated. Experiments show that the proposed ensemble methods can improve the recognition accuracy over an optimised single reference recogniser. Check if you have access through your login credentials or your institution.
ROMAN BERTOLAMI received his M. Computer Science from the University of Bern, Switzerland, in 2004. The topic of his master thesis was the rejection of words in off-line handwritten sentence recognition. He is now employed as research and lecture assistant in the research group of computer vision and artificial intelligence at the University of Bern. His current research interests include combination of multiple text line recognizer as well as confidence measures for handwritten text recognition systems. HORST BUNKE received his M.
Computer Science from the University of Erlangen, Germany. In 1984, he joined the University of Bern, Switzerland, where he is a professor in the Computer Science Department. 1996, Dean of the Faculty of Science from 1997 to 1998, and a member of the Executive Committee of the Faculty of Science from 2001 to 2003. In 2000 he also was Acting President of this organization. Horst Bunke is a Fellow of the IAPR, former Editor-in-Charge of the International Journal of Pattern Recognition and Artificial Intelligence, Editor-in-Chief of the Journal Electronic Letters of Computer Vision and Image Analysis, Editor-in-Chief of the book series on Machine Perception and Artificial Intelligence by World Scientific Publ.