Open Access Open Access  Restricted Access Subscription Access

Performance Comparison Online and Offline for Printed Jawi Character Recognition


Affiliations
1 Department of Electrical and Computer Engineering, Faculty of Engineering, Syiah Kuala University, Indonesia
 

Objectives: OCR for Jawi character both using offline or online application have been built. In this paper, we present performance comparison between online and offline feature extraction for Jawi character recognition. Methods/Analysis: This comparison is carried out to choose which version of the application that run faster to be applied in an OCR system. Both applications uses moment invariant feature extration, the online system uses PHP. On the other hand, the offline method uses Matlab. This research uses Database Printed Jawi (DPJ) as character samples. A 10 percent of total sample is taken as data-set for experiment. Findings: The result of this research shows that online application executes faster than offline process. Online OCR application is suggested to develop OCR systems. Novelty/Improvement: This comparison proposed for comparing and suggesting what kind of OCR system based would be considered.

Keywords

Moment Feature, OCR Performance Comparison, Online OCR, Printed Jawi Characters.
User

Abstract Views: 180

PDF Views: 0




  • Performance Comparison Online and Offline for Printed Jawi Character Recognition

Abstract Views: 180  |  PDF Views: 0

Authors

Ahmadiar
Department of Electrical and Computer Engineering, Faculty of Engineering, Syiah Kuala University, Indonesia
Sayed Muchallil
Department of Electrical and Computer Engineering, Faculty of Engineering, Syiah Kuala University, Indonesia

Abstract


Objectives: OCR for Jawi character both using offline or online application have been built. In this paper, we present performance comparison between online and offline feature extraction for Jawi character recognition. Methods/Analysis: This comparison is carried out to choose which version of the application that run faster to be applied in an OCR system. Both applications uses moment invariant feature extration, the online system uses PHP. On the other hand, the offline method uses Matlab. This research uses Database Printed Jawi (DPJ) as character samples. A 10 percent of total sample is taken as data-set for experiment. Findings: The result of this research shows that online application executes faster than offline process. Online OCR application is suggested to develop OCR systems. Novelty/Improvement: This comparison proposed for comparing and suggesting what kind of OCR system based would be considered.

Keywords


Moment Feature, OCR Performance Comparison, Online OCR, Printed Jawi Characters.



DOI: https://doi.org/10.17485/ijst%2F2017%2Fv10i12%2F151860