Total views : 165
Comparison Online to Offline Handwritten Jawi Character Recognition Application
Objectives: This paper investigates processing time comparison of handwritten Jawi characters recognition application between offline and online version. Methods/Analysis: The use of web server for processing offline tasks is considerable. This process is covered by translating offline application code into web-based programming language such as PHP. Total of 100 types of handwritten characters were used for this experiment. These characters were transformed using scaling transformation into four categories. Findings: The result shown online application has better performance than offline. The online application succeeds to extract moment feature of handwritten characters. Novelty/Improvement: The comparison was performed for choosing better Optical Character recognition (OCR) application system: online or offline method.
Handwritten Jawi Characters, OCR Performance Comparison, Online OCR, Moment Feature.
- Saddami K, Munadi K, Arnia F. A database of printed Jawi character image. IEEE Press: Proceedings of 2015 3rd International Conference on Image Information Processing, ICIIP 2015. 2015; p. 56-9. Available from: Crossref.
- Arnia F, Munadi K, Fardian F, Muchallil S. Improvement of binarization performance by applying dct as preprocessing procedure. IEEE Press: Proceedings of 2014 6th International Symposium on Communications, Control, and Signal Processing, ICCSP 2014. 2014; p. 128-32.
- Muchallil S, Arnia F, Munadi K, Fardian. Performance comparison of denoising methods for historical documents. Jurnal Teknologi. 2015; 77(22):137-43. Available from: Crossref.
- Fardian F, Arnia F, Muchallil S, Munadi K. Identification of most suitable binarisation methods for acehnese ancient manuscripts restoration software user guide. Jurnal Teknologi. 2015; 77(22):95-102. Available from: 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.
- Otsu N. A threshold selection method from gray-level histograms. Automatica. 1975; 11(285-296):23-7.
- Sauvola J, Pietikainen M. Adaptive document image binarization. Pattern Recognition. 2000; 33(2):225-36. Available from: 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. Available from: Crossref.
- Su B, Lu S, Tan CL. Robust document image binarization technique for degraded document images. IEEE Transactions on Image Processing. 2013; 22(4):1408-17. Available from: Crossref. PMid:23221822.
- Nina O, Morse B, Barrett W. A recursive Otsu thresholding method for scanned document binarization. 2011 IEEE Workshop on Applications of Computer Vision, (WACV 2011). 2011; 307-14.
- Khurshid K, Siddiqi I, Faure C, Vincent N. Comparison of Niblack inspired Binarization methods for ancient documents. IS&T/SPIE Electronic Imaging. 2009; p. 72470U-72470U. Available from: Crossref.
- Shih FY. New Jersey: John Wiley and Sons, Inc.: Image Processing and Pattern Recognition: Fundamentals and Techniques. 2010. Available from: Crossref.
- Hu M-K. Visual pattern recognition by moment invariants. IRE Transactions on Information Theory. 1962; 8(2):17987. Available from: Crossref.
- Gonzalez, RC, Woods RE, Eddins SL. New Jersey: Pearson Prantice Hall: Digital Image Processing Using Matlab. 2004.
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.