Handwritten Word Recognition Using Conditional Random Fields
Authors:
- S. ShettySSS. Shetty
- H. SrinivasanHSH. Srinivasan
- S. SrihariSSS. Srihari
- 1 September 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)
- Vol. 2 (15205363) , 1098-1102
Abstract
The paper describes a lexicon driven approach for word recognition on handwritten documents using conditional random fields (CRFs). CRFs are discriminative models and do not make any assumptions about the underlying data and hence are known to be superior to hidden Markov models (HMMs) for sequence labeling problems. For word recognition, the document is first segmented into word images using an existing neural network based algorithm. Each word image is then over segmented into a number of small segments such that the combination of segments forms character images. Segment(s) is/are labeled as characters with probability evaluated from the CRF model. The total probability of a word image representing an entry from the lexicon is computed using a dynamic programming algorithm which evaluates the optimal combination of segments.Keywords
This publication has 3 references indexed in Scilit:
- A statistical approach to line segmentation in handwritten documents2007
- Exploring the Use of Conditional Random Field Models and HMMs for Historical Handwritten Document Recognition2006
- A lexicon driven approach to handwritten word recognition for real-time applicationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997