An evolutionary harmony search algorithm with dominant point detection for recognition-based segmentation of online Arabic text recognition
This paper highlights a novel strategy for online Arabic text recognition using a hybrid Genetic Algorithm (GA) and Harmony Search algorithm (HS). The strategy is divided into two phases: text segmentation using dominant point detection, and recognition-based segmentation using GA and HS. At firs...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
Elsevier
2014
|
| Subjects: |
| _version_ | 1797010001773985792 |
|---|---|
| author | Moayad, Yousif Potrus Ngah, Umi Kalthum Bestoun S. , Ahmed |
| author_facet | Moayad, Yousif Potrus Ngah, Umi Kalthum Bestoun S. , Ahmed |
| author_sort | Moayad, Yousif Potrus |
| collection | USM |
| description | This paper highlights a novel strategy for online Arabic text recognition using a hybrid
Genetic Algorithm (GA) and Harmony Search algorithm (HS). The strategy is divided into two
phases: text segmentation using dominant point detection, and recognition-based segmentation
using GA and HS. At first, the pre-segmentation algorithm uses a modified dominant point detection
algorithm to mark a minimal number of points which defines the text skeleton. The generated
text skeleton from this process is expressed as directional vector, using 6-directional model, to minimize
the effect of character body on segmentation process. Then, GA and HS algorithms are used
as recognition-based segmentation phase for text and character recognition respectively. For the
segmentation based recognition, binary GA is used to explore different combinations of segmentation
points which gives the best score, while HS is integrated inside the GA segmentation to explore
the best character score produced from matching the character with different characters stored in
the database. In order to initially calibrate and test the system, a locally collected text dataset
was used that contains 4500 Arabic words. The algorithm scored a 93.4% successful word recognition
rate. Finally, the system was tested on the benchmark ADAB dataset 2 consist of 7851 Arabic
words and it scored a successful recognition rate in the range of 94–96%. |
| first_indexed | 2024-03-06T15:13:34Z |
| format | Article |
| id | usm.eprints-38286 |
| institution | Universiti Sains Malaysia |
| last_indexed | 2024-03-06T15:13:34Z |
| publishDate | 2014 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | usm.eprints-382862018-01-08T09:33:43Z http://eprints.usm.my/38286/ An evolutionary harmony search algorithm with dominant point detection for recognition-based segmentation of online Arabic text recognition Moayad, Yousif Potrus Ngah, Umi Kalthum Bestoun S. , Ahmed TK1-9971 Electrical engineering. Electronics. Nuclear engineering This paper highlights a novel strategy for online Arabic text recognition using a hybrid Genetic Algorithm (GA) and Harmony Search algorithm (HS). The strategy is divided into two phases: text segmentation using dominant point detection, and recognition-based segmentation using GA and HS. At first, the pre-segmentation algorithm uses a modified dominant point detection algorithm to mark a minimal number of points which defines the text skeleton. The generated text skeleton from this process is expressed as directional vector, using 6-directional model, to minimize the effect of character body on segmentation process. Then, GA and HS algorithms are used as recognition-based segmentation phase for text and character recognition respectively. For the segmentation based recognition, binary GA is used to explore different combinations of segmentation points which gives the best score, while HS is integrated inside the GA segmentation to explore the best character score produced from matching the character with different characters stored in the database. In order to initially calibrate and test the system, a locally collected text dataset was used that contains 4500 Arabic words. The algorithm scored a 93.4% successful word recognition rate. Finally, the system was tested on the benchmark ADAB dataset 2 consist of 7851 Arabic words and it scored a successful recognition rate in the range of 94–96%. Elsevier 2014 Article PeerReviewed Moayad, Yousif Potrus and Ngah, Umi Kalthum and Bestoun S. , Ahmed (2014) An evolutionary harmony search algorithm with dominant point detection for recognition-based segmentation of online Arabic text recognition. Ain Shams Engineering Journal, 2014 (5). pp. 1129-1139. ISSN 2090-4479 http://dx.doi.org/10.1016/j.asej.2014.05.003 |
| spellingShingle | TK1-9971 Electrical engineering. Electronics. Nuclear engineering Moayad, Yousif Potrus Ngah, Umi Kalthum Bestoun S. , Ahmed An evolutionary harmony search algorithm with dominant point detection for recognition-based segmentation of online Arabic text recognition |
| title | An evolutionary harmony search algorithm with
dominant point detection for recognition-based
segmentation of online Arabic text recognition |
| title_full | An evolutionary harmony search algorithm with
dominant point detection for recognition-based
segmentation of online Arabic text recognition |
| title_fullStr | An evolutionary harmony search algorithm with
dominant point detection for recognition-based
segmentation of online Arabic text recognition |
| title_full_unstemmed | An evolutionary harmony search algorithm with
dominant point detection for recognition-based
segmentation of online Arabic text recognition |
| title_short | An evolutionary harmony search algorithm with
dominant point detection for recognition-based
segmentation of online Arabic text recognition |
| title_sort | evolutionary harmony search algorithm with dominant point detection for recognition based segmentation of online arabic text recognition |
| topic | TK1-9971 Electrical engineering. Electronics. Nuclear engineering |
| work_keys_str_mv | AT moayadyousifpotrus anevolutionaryharmonysearchalgorithmwithdominantpointdetectionforrecognitionbasedsegmentationofonlinearabictextrecognition AT ngahumikalthum anevolutionaryharmonysearchalgorithmwithdominantpointdetectionforrecognitionbasedsegmentationofonlinearabictextrecognition AT bestounsahmed anevolutionaryharmonysearchalgorithmwithdominantpointdetectionforrecognitionbasedsegmentationofonlinearabictextrecognition AT moayadyousifpotrus evolutionaryharmonysearchalgorithmwithdominantpointdetectionforrecognitionbasedsegmentationofonlinearabictextrecognition AT ngahumikalthum evolutionaryharmonysearchalgorithmwithdominantpointdetectionforrecognitionbasedsegmentationofonlinearabictextrecognition AT bestounsahmed evolutionaryharmonysearchalgorithmwithdominantpointdetectionforrecognitionbasedsegmentationofonlinearabictextrecognition |