logo Idiap Research Institute        
 [BibTeX] [Marc21]
Offline Cursive Word Recognition using Continuous Density Hidden Markov Models trained with PCA or ICA Features
Type of publication: Conference paper
Citation: vincia01c-conf
Booktitle: Proceedings of International Conference on Pattern Recognition
Volume: III
Year: 2002
Address: Quebec City (Canada)
Crossref: vincia01c:
Abstract: This work presents an Offline Cursive Word Recognition System dealing with single writer samples. The system is a continuous density hiddden Markov model trained using either the raw data, or data transformed using Principal Component Analysis or Independent Component Analysis. Both techniques significantly improved the recognition rate of the system. Preprocessing, normalization and feature extraction are described in detail as well as the training technique adopted. Several experiments were performed using a publicly available database. The accuracy obtained is the highest presented in the literature over the same data.
Userfields: ipdmembership={vision},
Projects Idiap
Authors Vinciarelli, Alessandro
Bengio, Samy
Added by: [UNK]
Total mark: 0
  • rr01-46-conf.pdf
  • rr01-46-conf.ps.gz