Offline Handwritten Devanagari Word Recognition: A Holistic Approach Based on Directional Chain Code Feature and HMM
- 1 December 2008
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2008 International Conference on Information Technology
- p. 203-208
- https://doi.org/10.1109/icit.2008.33
Abstract
A hidden Markov model (HMM) based approach is proposed for recognition of offline handwritten Devanagari words. The histogram of chain-code directions in the image-strips, scanned from left to right by a sliding window, is used as the feature vector. A continuous density HMM is proposed to recognize a word image. In our approach the states of the HMM are not determined a priori, but are determined automatically based on a database of handwritten word images. A handwritten word image is assumed to be a string of several image frame primitives. These are in fact the states of the proposed HMM and are found using a certain mixture distribution. One HMM is constructed for each word. To classify an unknown word image, its class conditional probability for each HMM is computed. The class that gives highest such probability is finally selected.Keywords
This publication has 9 references indexed in Scilit:
- Hidden Markov models combining discrete symbols and continuous attributes in handwriting recognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Handwritten Farsi (Arabic) word recognition: a holistic approach using discrete HMMPattern Recognition, 2001
- An HMM-based approach for off-line unconstrained handwritten word modeling and recognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999
- An off-line cursive handwriting recognition systemIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Handwritten word recognition using segmentation-free hidden Markov modeling and segmentation-based dynamic programming techniquesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- Off-line cursive handwriting recognition using hidden markov modelsPattern Recognition, 1995
- Variable duration hidden Markov model and morphological segmentation for handwritten word recognitionIEEE Transactions on Image Processing, 1995
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989
- A Threshold Selection Method from Gray-Level HistogramsIEEE Transactions on Systems, Man, and Cybernetics, 1979