Hidden Markov model-based ensemble methods for offline handwritten text line recognition |
| |
| Authors: | Roman Bertolami Horst Bunke |
| |
| Affiliation: | 1. Department of Computer Science, South China University of Technology, Guangzhou, China;2. Qatar Computing Research Institute, Qatar Foundation for Education, Science and Community Development, Doha, Qatar;3. Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong;1. Escuela de Enseñanzas Técnicas, Departamento de Ciencias Físicas, Matemáticas y de la Computación, Universidad CEU Cardenal Herrera, C/San Bartolomé 55, 46155 Alfara del Patriarca, Valencia, Spain;2. Departamento de Sistemas Informáticos y Computación, Universitat Politècnica de València, Valencia, Spain;3. Faculty of Information Science and Electrical Engineering, Kyushu University, Japan;4. Institute for Computer Science and Applied Mathematics, University of Bern, Bern, Switzerland;1. College of Mechanical & Electrical Engineering, Shaanxi University of Science & Technology, Xi’an, Shaanxi 710021, China;2. Shaanxi Environmental Protection Industry Group.Co., Ltd, Xi’an, Shaanxi 710100, China;3. Dongfang Electric Machinery Co., Ltd, Deyang, Sichuan 618000, China;4. Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China;1. Key Laboratory of Computational Linguistics, Peking University, Ministry of Education, Beijing, China;2. Department of Computing, The Hong Kong Polytechnic University, Hong Kong;3. Natural Language Computing Group, Microsoft Research Asia, Beijing, China |
| |
| Abstract: | This paper investigates various ensemble methods for offline handwritten text line recognition. To obtain 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. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
