Performance analysis of character segmentation approach for cursive script recognition on benchmark database
This paper analyzes the improved performance of our proposed character segmentation algorithm in comparison to others presented in the literature from accuracy and computational complexity points of view. The training set is taken from IAM and test set is from CEDAR benchmark databases. Segmentation...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Published: |
Elsevier Inc.
2011
|
| Subjects: |
| _version_ | 1796856578459041792 |
|---|---|
| author | Rehman, Amjad Saba, Tanzila |
| author_facet | Rehman, Amjad Saba, Tanzila |
| author_sort | Rehman, Amjad |
| collection | ePrints |
| description | This paper analyzes the improved performance of our proposed character segmentation algorithm in comparison to others presented in the literature from accuracy and computational complexity points of view. The training set is taken from IAM and test set is from CEDAR benchmark databases. Segmentation is achieved by analyzing characters geometric features and ligatures which are strong points for segmentation in cursive handwritten words. Following pre-processing, a new heuristic technique is employed to over-segment each word at potential segmentation points. Subsequently, a simple criterion is adopted to come out with fine segmentation points based on character shape analysis. Finally, the fine segmentation points are fed to train neural network for validating segment points to enhance segmentation accuracy. Based on detailed analysis and comparison, it is observed that proposed approach enhances the cursive script segmentation accuracy with minimum computational complexity. |
| first_indexed | 2024-03-05T18:45:08Z |
| format | Article |
| id | utm.eprints-29566 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T18:45:08Z |
| publishDate | 2011 |
| publisher | Elsevier Inc. |
| record_format | dspace |
| spelling | utm.eprints-295662019-04-25T01:15:31Z http://eprints.utm.my/29566/ Performance analysis of character segmentation approach for cursive script recognition on benchmark database Rehman, Amjad Saba, Tanzila QA75 Electronic computers. Computer science This paper analyzes the improved performance of our proposed character segmentation algorithm in comparison to others presented in the literature from accuracy and computational complexity points of view. The training set is taken from IAM and test set is from CEDAR benchmark databases. Segmentation is achieved by analyzing characters geometric features and ligatures which are strong points for segmentation in cursive handwritten words. Following pre-processing, a new heuristic technique is employed to over-segment each word at potential segmentation points. Subsequently, a simple criterion is adopted to come out with fine segmentation points based on character shape analysis. Finally, the fine segmentation points are fed to train neural network for validating segment points to enhance segmentation accuracy. Based on detailed analysis and comparison, it is observed that proposed approach enhances the cursive script segmentation accuracy with minimum computational complexity. Elsevier Inc. 2011-05 Article PeerReviewed Rehman, Amjad and Saba, Tanzila (2011) Performance analysis of character segmentation approach for cursive script recognition on benchmark database. Digital Signal Processing, 21 (3). pp. 486-490. ISSN 1051-2004 http://dx.doi.org/10.1016/j.dsp.2011.01.016 DOI:10.1016/j.dsp.2011.01.016 |
| spellingShingle | QA75 Electronic computers. Computer science Rehman, Amjad Saba, Tanzila Performance analysis of character segmentation approach for cursive script recognition on benchmark database |
| title | Performance analysis of character segmentation approach for cursive script recognition on benchmark database |
| title_full | Performance analysis of character segmentation approach for cursive script recognition on benchmark database |
| title_fullStr | Performance analysis of character segmentation approach for cursive script recognition on benchmark database |
| title_full_unstemmed | Performance analysis of character segmentation approach for cursive script recognition on benchmark database |
| title_short | Performance analysis of character segmentation approach for cursive script recognition on benchmark database |
| title_sort | performance analysis of character segmentation approach for cursive script recognition on benchmark database |
| topic | QA75 Electronic computers. Computer science |
| work_keys_str_mv | AT rehmanamjad performanceanalysisofcharactersegmentationapproachforcursivescriptrecognitiononbenchmarkdatabase AT sabatanzila performanceanalysisofcharactersegmentationapproachforcursivescriptrecognitiononbenchmarkdatabase |