Segmentation free Bangla OCR using HMM: Training and recognition
Includes bibliographical references (page 7-8).
| Main Authors: | , , |
|---|---|
| Outros autores: | |
| Formato: | Artigo |
| Idioma: | English |
| Publicado: |
BRAC University
2010
|
| Subjects: | |
| Acceso en liña: | http://hdl.handle.net/10361/666 |
| id |
10361-666 |
|---|---|
| record_format |
dspace |
| spelling |
10361-6662019-09-29T05:27:30Z Segmentation free Bangla OCR using HMM: Training and recognition Hasnat, Md. Abul Habib, S. M. Murtoza Khan, Mumit Center for Research on Bangla language processing (CRBLP), BRAC University Optical character recognition (OCR) Hidden Markov Model (HMM) HTK Discrete cosine transform (DCT) Includes bibliographical references (page 7-8). The wide area of the application of HMM is in Speech Recognition where each spoken word is considered as a single unit to be recognized from the trained word network. Using this concept some research has been done for character recognition. In this paper, we present the training and recognition mechanism of a Hidden Markov Model (HMM) based multi font supported Optical Character Recognition (OCR) system for Bangla character. In our approach the central idea is separate HMM model for each segmented character or word. We emphasize on word level segmentation and like to consider the single character as a word when the character appears alone after segmentation process is done. The system uses HTK toolkit for data preparation, model training from multiple samples and recognition. Features of each trained character are calculated by applying Discrete Cosine Transform (DCT) to each pixel value of the character image where the image is divided into several frames according to its size. The extracted features of each frame are used as discrete probability distributions that will be given as input parameter to each HMM model. In case of recognition a model for each separated character or word is build up using the same approach. This model is given to the HTK toolkit to perform the recognition using Viterbi Decoding. The experimental result shows significant performance. Md. Abul Hasnat S. M. Murtoza Habib Mumit Khan 2010-12-06T10:37:04Z 2010-12-06T10:37:04Z 2007 2007 Article http://hdl.handle.net/10361/666 en application/pdf BRAC University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
Optical character recognition (OCR) Hidden Markov Model (HMM) HTK Discrete cosine transform (DCT) |
| spellingShingle |
Optical character recognition (OCR) Hidden Markov Model (HMM) HTK Discrete cosine transform (DCT) Hasnat, Md. Abul Habib, S. M. Murtoza Khan, Mumit Segmentation free Bangla OCR using HMM: Training and recognition |
| description |
Includes bibliographical references (page 7-8). |
| author2 |
Center for Research on Bangla language processing (CRBLP), BRAC University |
| author_facet |
Center for Research on Bangla language processing (CRBLP), BRAC University Hasnat, Md. Abul Habib, S. M. Murtoza Khan, Mumit |
| format |
Article |
| author |
Hasnat, Md. Abul Habib, S. M. Murtoza Khan, Mumit |
| author_sort |
Hasnat, Md. Abul |
| title |
Segmentation free Bangla OCR using HMM: Training and recognition |
| title_short |
Segmentation free Bangla OCR using HMM: Training and recognition |
| title_full |
Segmentation free Bangla OCR using HMM: Training and recognition |
| title_fullStr |
Segmentation free Bangla OCR using HMM: Training and recognition |
| title_full_unstemmed |
Segmentation free Bangla OCR using HMM: Training and recognition |
| title_sort |
segmentation free bangla ocr using hmm: training and recognition |
| publisher |
BRAC University |
| publishDate |
2010 |
| url |
http://hdl.handle.net/10361/666 |
| work_keys_str_mv |
AT hasnatmdabul segmentationfreebanglaocrusinghmmtrainingandrecognition AT habibsmmurtoza segmentationfreebanglaocrusinghmmtrainingandrecognition AT khanmumit segmentationfreebanglaocrusinghmmtrainingandrecognition |
| _version_ |
1814308867294625792 |