Total views : 140
Performance Comparison Online and Offline for Printed Jawi Character Recognition
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.
Moment Feature, OCR Performance Comparison, Online OCR, Printed Jawi Characters.
- Muchallil S, Arnia F, Munadi K, Fardian. Performance comparison of denoising methods for historical documents. Jurnal Teknologi. 2015; 77(22):137–43. Crossref
- Omar K. Jawi handwritten text recognition using multilevel classifier. PhD Thesis, Universiti Putra Malaysia; 2000.
- Manaf M. Jawi handwritten text recognition using recurrent bama neural networks. PhD Thesis, Universiti Kebangsaan Malaysia; 2002.
- Nasrudin MF, Petrou M, Kotoulas L. Jawi character recognition using the trace transform. 2010 Seventh International Conference on Computer Graphics, Imaging and Visualization (CGIV); 2010. p. 151–6. Crossref
- Nasrudin MF, Petrou M. Offline handwritten Jawi recognition using the trace transform. 2011 International Conference on Pattern Analysis and Intelligent Robotics (ICPAIR); 2011. p. 87–91. Crossref
- Razak Z, Rosli S, Mashkuri Y. Hardware design of on-line jawi character recognition chip using discrete wavelet transform. Proceedings of Eighth International Conference on Document Analysis and Recognition; 2005. p. 91–5.
- Razak Z, Zulkiflee K, Noor NM, Salleh R, Yaacob M. Off-line handwritten Jawi character segmentation using histogram normalization and sliding window approach for hardware implementation. Malaysian Journal of Computer Science. 2009; 22(1):34–43.
- Sauvola J, Pietikäinen M. Adaptive document image binarization. Pattern Recognition. 2000; 33(2):225–36. Crossref
- Otsu N. A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 1979; 9(1):62–6. Crossref
- Lu S, Su B, Tan CL. Document image binarization using background estimation and stroke edges. International Journal on Document Analysis and Recognition. 2010; 13(4):303–14. Crossref
- Su B, Lu S, Tan CL. Robust document image binarization technique for degraded document images. IEEE Transactions on Image Process. 2013; 22(4):1408–17. Crossref
- Hu M-K. Visual pattern recognition by moment invariants. IRE Transactions on Information Theory. 1962; 8(2):179– 87. Crossref
- Arnia F, Munadi K, Fardian F, Muchallil S. Improvement of binarization performance by applying dct as preprocessing procedure. Proceedings of 2014 6th International Symposium on Communications, Control, and Signal Processing, ICCSP 2014. IEEE Press; 2014. p. 128–32.
- Gonzalez RC, Woods RE, Eddins SL. Digital image processing using Matlab, New Jersey: Pearson Prantice Hall; 2004.
- Shih FY. Image processing and pattern recognition: Fundamentals and techniques. New Jersey: John Wiley and Sons, Inc; 2010. Saddami K, Munadi K, Arnia F. A database of printed Jawi character image. Proceedings of 2015 3rd International Conference on Image Information Processing, ICIIP 2015. IEEE Press; 2015. p. 56–9.
- Saddami K, Munadi K, Arnia F. A database of printed Jawi character image. In: Proceedings of 2015 3rd International Conference on Image Information Processing, ICIIP 2015. IEEE Press; 2015. p. 56–59. Crossref
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.