|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
2011 International Conference on Document Analysis and Recognition
Handwritten and Typewritten Text Identification and Recognition Using Hidden Markov Models
Beijing, China
September 18-September 21
ISBN: 978-0-7695-4520-2
| ASCII Text | x | ||
| Huaigu Cao, Rohit Prasad, Prem Natarajan, "Handwritten and Typewritten Text Identification and Recognition Using Hidden Markov Models," Document Analysis and Recognition, International Conference on, pp. 744-748, 2011 International Conference on Document Analysis and Recognition, 2011. | |||
| BibTex | x | ||
| @article{ 10.1109/ICDAR.2011.155, author = {Huaigu Cao and Rohit Prasad and Prem Natarajan}, title = {Handwritten and Typewritten Text Identification and Recognition Using Hidden Markov Models}, journal ={Document Analysis and Recognition, International Conference on}, volume = {0}, year = {2011}, issn = {1520-5363}, pages = {744-748}, doi = {http://doi.ieeecomputersociety.org/10.1109/ICDAR.2011.155}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - Document Analysis and Recognition, International Conference on TI - Handwritten and Typewritten Text Identification and Recognition Using Hidden Markov Models SN - 1520-5363 SP744 EP748 A1 - Huaigu Cao, A1 - Rohit Prasad, A1 - Prem Natarajan, PY - 2011 KW - optical character recognition KW - hidden Markov model KW - Gaussian mixture model VL - 0 JA - Document Analysis and Recognition, International Conference on ER - | |||
We present a system for identification and recognition of handwritten and typewritten text from document images using hidden Markov models (HMMs) in this paper. Our text type identification uses OCR decoding to generate word boundaries followed by word-level handwritten/typewritten identification using HMMs. We show that the contextual constraints from the HMM significantly improves the identification performance over the conventional Gaussian mixture model (GMM)-based method. Type identification is then used to estimate the frame sample rates and frame width of feature sequences for HMM OCR system for each type independently. This type-dependent approach to computing the frame sample rate and frame width shows significant improvement in OCR accuracy over type-independent approaches.
Index Terms:
optical character recognition, hidden Markov model, Gaussian mixture model
Citation:
Huaigu Cao, Rohit Prasad, Prem Natarajan, "Handwritten and Typewritten Text Identification and Recognition Using Hidden Markov Models," icdar, pp.744-748, 2011 International Conference on Document Analysis and Recognition, 2011
Usage of this product signifies your acceptance of the Terms of Use.