Abstract
This paper is aimed at improving the performance of the word recognition system (WRS) of handwritten Arabic text by extracting features in the frequency domain using the Stationary Wavelet Transform (SWT) method using machine learning, which is a wavelet transform approach created to compensate for the absence of translation invariance in the Discrete Wavelets Transform (DWT) method. The proposed SWT-WRS of Arabic handwritten text consists of three main processes: word normalization, feature extraction based on SWT, and recognition. The proposed SWT-WRS based on the SWT method is evaluated on the IFN/ENIT database applying the Gaussian, linear, and polynomial support vector machine, the k-nearest neighbors, and ANN classifiers. ANN performance was assessed by applying the Bayesian Regularization (BR) and Levenberg-Marquardt (LM) training methods. Numerous wavelet transform (WT) families are applied, and the results prove that level 19 of the Daubechies family is the best WT family for the proposed SWT-WRS. The results also confirm the effectiveness of the proposed SWT-WRS in improving the performance of handwritten Arabic word recognition using machine learning. Therefore, the suggested SWT-WRS overcomes the lack of translation invariance in the DWT method by eliminating the up-and-down samplers from the proposed machine learning method.
- [1] . 2017. Artificial immune algorithm for handwritten Arabic word recognition. The International Arab Journal of Information Technology 14, 2 (2017), 186–194.Google Scholar
- [2] . 2015. Word-based Arabic handwritten recognition using SVM classifier with a reject option. 15th International Conference on Intelligent Systems Design and Applications (ISDA). 64–68.
DOI: DOI: 10.1109/ISDA.2015.7489190Google ScholarCross Ref
- [3] . 2013. Offline Arabic handwritten text recognition: A survey. ACM Computing Surveys (CSUR) 45, 2 (2013), 23. http://doi.acm.org/10.1145/2431211.2431222 Google Scholar
Digital Library
- [4] . 2002. Off-line Arabic character recognition – a review. 2002. Pattern Anal Appl 5 (2002), 31–45. https://doi.org/10.1007/s100440200004 Google Scholar
Digital Library
- [5] . 2011. Handwritten Arabic word recognition based on ridgelet transform and support vector machines. 2011 International Conference on High Performance Computing & Simulation. 357–361.
DOI: DOI: 10.1109/HPCSim.2011.5999846Google ScholarCross Ref
- [6] . 2019. Handwritten Arabic text recognition using principal component analysis and support vector machines. International Journal of Advanced Computer Science and Applications 10, 12 (2019), 1–6.
DOI:
http://dx.doi.org/10.14569/IJACSA.2019.0101227Google Scholar
Cross Ref
- [7] . 2018. A holistic technique for an Arabic OCR system. Journal of Imaging 4, 1 (2018), 1–11. https://doi.org/10.3390/jimaging4010006Google Scholar
- [8] World Arabic Language Day. 2017. UNESCO. Archived from the original on 27 October 2017. Accessed 21 January 2020.Google Scholar
- [9] . 2014. Skeleton extraction: Comparison of five methods on the Arabic IFN/ENIT database. 6th International Conference on Computer Science and Information Technology (CSIT). 50–59.
DOI: DOI: 10.1109/CSIT.2014.6805978Google ScholarCross Ref
- [10] . 2014. A skew detection and correction technique for Arabic script text-line based on subwords bounding. 2014 IEEE International Conference in Computational Intelligence and Computing Research (ICCIC). 1–5.
DOI: DOI: 10.1109/ICCIC.2014.7238501Google ScholarCross Ref
- [11] . 2016. A novel baseline estimation method for Arabic handwritten text based on exploited components of Voronoi diagrams. International Arab Journal of Information Technology 13, 3 (2016), 977–1003.Google Scholar
- [12] . 2015. A preprocessing model for hand-written Arabic texts based on Voronoi diagrams. International Journal of Computer Science and Information Technology 7, 6 (2015), 1–18. https://doi.org/10.5121/ijcsit.2015.7601Google Scholar
Cross Ref
- [13] . 2015. A review of feature extraction techniques for handwritten Arabic text recognition. 2015 International Conference on Electrical and Information Technologies (ICEIT). 241–245.
DOI: DOI: 10.1109/EITech.2015.7162979Google ScholarCross Ref
- [14] . 2010. Word based off-line handwritten Arabic classification and recognition: Design of automatic recognition system for large vocabulary offline handwritten Arabic words using machine learning approaches. Ph.D. dissertation, University of Bradford.Google Scholar
- [15] . 2011. Word-based handwritten Arabic scripts recognition using dynamic Bayesian network. In Proceedings of the 5th International Conference on Information Technology.Google Scholar
- [16] . 2005. Arabic handwriting recognition using baseline dependent features and hidden Markov modeling. In Eighth International Conference on Document Analysis and Recognition (ICDAR'05). 893–897.
DOI: DOI: 10.1109/ICDAR.2005.53 Google ScholarDigital Library
- [17] . 2011. Offline Arabic text recognition–an overview. World of Computer Science and Information Technology Journal (WCSIT) 1, 5 (2011), 184–192.Google Scholar
- [18] . 2017. Proposed handwriting Arabic words classification based on discrete wavelet transform and support vector machine. Iraqi Journal of Science 58, 2C (2017), 1159–1168.Google Scholar
- [19] . 2015. Handwriting word recognition based on SVM classifier. International Journal of Advanced Computer Science & Applications 1 (2015), 64–68.Google Scholar
- [20] . 2011. A novel word based Arabic handwritten recognition system using SVM classifier. In International Conference on Electronic Commerce, Web Application, and Communication. Springer, 163–171. https://doi.org/10.1007/978-3-642-20367-1_26Google Scholar
Cross Ref
- [21] . 2006. Classification of magnetic resonance brain images using wavelets as input to support vector machine and neural network. Biomedical Signal Processing and Control 1, 1 (2006), 86–92. https://doi.org/10.1016/j.bspc.2006.05.002Google Scholar
Cross Ref
- [22] . 2017. Facial expression recognition using stationary wavelet transform features. Mathematical Problems in Engineering. 1–9. https://doi.org/10.1155/2017/9854050Google Scholar
Cross Ref
- [23] . 2015. Face recognition using stationary wavelet transform and neural network with support vector machine. Iraqi Journal of Science 56, 1B (2015), 520–530.Google Scholar
- [24] . 2020. Survey of offline Arabic handwriting word recognition. In International Conference on Soft Computing and Data Mining. Springer, Cham, 358–372. https://doi.org/10.1007/978-3-030-36056-6_34Google Scholar
Cross Ref
- [25] . 2001. Handwritten Farsi (Arabic) word recognition: A holistic approach using discrete HMM. Pattern Recognition 34, 5 (2001), 1057–1065. https://doi.org/10.1016/S0031-3203(00)00051-0Google Scholar
Cross Ref
- [26] . 2006. Comparison of two different feature sets for offline recognition of handwritten Arabic words. Tenth International Workshop on Frontiers in Handwriting Recognition.Google Scholar
- [27] . 2009. Krawtchouk moment feature extraction for neural Arabic handwritten words recognition. 2009 International Conference on Multimedia Computing and Systems. 443–448.
DOI: DOI: 10.1109/MMCS.2009.5256656Google ScholarCross Ref
- [28] . 2010. Principal components analysis for Arabic sub-word recognition. 2010 International Conference on Intelligent Network and Computing (ICINC 2010). 432–434.Google Scholar
- [29] . 2011. Offline handwritten Arabic cursive text recognition using hidden Markov models and re-ranking. Pattern Recognition Letters 32, 8 (2011), 1081–1088. https://doi.org/10.1016/j.patrec.2011.02.006 Google Scholar
Digital Library
- [30] . 2010. Holistic Urdu handwritten word recognition using support vector machine. 20th International Conference on Pattern Recognition. 1900–1903.
DOI: DOI: 10.1109/ICPR.2010.468 Google ScholarDigital Library
- [31] . 2012. Off-line handwritten Arabic word recognition using SVMs with normalized poly kernel. In International Conference on Neural Information Processing. Springer, 85–91. https://doi.org/10.1007/978-3-642-34481-7_11 Google Scholar
Digital Library
- [32] . 2012. Classifiers combination for Arabic words recognition: Application to handwritten Algerian city names. International Conference on Image and Signal Processing. Springer, 562–570. https://doi.org/10.1007/978-3-642-31254-0_64 Google Scholar
Digital Library
- [33] . 2015. Arabic handwritten words off-line recognition based on HMMs and DBNs. 13th International Conference on Document Analysis and Recognition (ICDAR). 51–55.
DOI: DOI: 10.1109/ICDAR.2015.7333724 Google ScholarDigital Library
- [34] . 2017. Arabic handwriting recognition using sequential minimal optimization. 1st International Workshop on Arabic Script Analysis and Recognition (ASAR). 79–84.
DOI: DOI: 10.1109/ASAR.2017.8067764Google ScholarCross Ref
- [35] . 2018. Convolutional neural network and BLSTM for offline Arabic handwriting recognition. In 2018 International Arab Conference on Information Technology (ACIT). 1–6.
DOI: DOI: 10.1109/ACIT.2018.8672667Google ScholarCross Ref
- [36] . 2018. Convolutional feature learning and CNN based HMM for Arabic handwriting recognition. In International Conference on Image and Signal Processing. 265–274. https://doi.org/10.1007/978-3-319-94211-7_29Google Scholar
Cross Ref
- [37] . 2018. Recognition of cursive Arabic handwritten text using embedded training based on hidden Markov models. International Journal of Pattern Recognition and Artificial Intelligence 32, 1 (2018), 1860007.Google Scholar
Cross Ref
- [38] . 2018. Statistical geometric components of straight lines (SGCSL) feature extraction method for offline Arabic/Persian handwritten words recognition. IET Image Processing 12, 9 (2018), 1606–1616.Google Scholar
Cross Ref
- [39] . 2019. Deep-learning ensemble for offline Arabic handwritten words recognition. In 2019 14th International Conference on Computer Engineering and Systems (ICCES). IEEE, 40–45.
DOI: DOI: 10.1109/ICCES48960.2019.9068184Google ScholarCross Ref
- [40] . 2019. Bayesian versus convolutional networks for Arabic handwriting recognition. Arab J Sci Eng 44, 9301–9319. https://doi.org/10.1007/s13369-019-03939-yGoogle Scholar
Cross Ref
- [41] . 2020. Handwritten Arabic words recognition system based on hog and Gabor filter descriptors. In 2020 1st International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET). IEEE, 1–4.
DOI: DOI: 10.1109/IRASET48871.2020.9092067Google ScholarCross Ref
- [42] . 2021. Recognition of offline handwritten Arabic words using a few structural features. Computers, Materials & Continua 66, 3 (2021), 2875–2889. doi:
DOI:
10.32604/cmc.2021.013744Google Scholar
Cross Ref
- [43] . 1995. The stationary wavelet transform and some statistical applications. In Wavelets and Statistics. Springer, 281–299.
DOI:
https://doi.org/10.1007/978-1-4612-2544-7_17Google Scholar
Cross Ref
- [44] . 2007. Wavelet transforms and efficient implementation on the GPU. University of Oslo, Master's thesis.Google Scholar
- [45] . 2010. Feature extraction of brain MRI by stationary wavelet transform and its applications. Journal of Biological Systems. 18, (spec01), 115–132. https://doi.org/10.1142/S0218339010003652Google Scholar
Cross Ref
- [46] . 2015. Magnetic resonance brain image classification via stationary wavelet transform and generalized eigenvalue proximal support vector machine. Journal of Medical Imaging and Health Informatics 5, 7 (2015), 1395–1403. https://doi.org/10.1166/jmihi.2015.1542Google Scholar
Cross Ref
- [47] . 2016. Synchronous multi-stream hidden Markov model for offline Arabic handwriting recognition without explicit segmentation. Neurocomputing. 214, 958–971. https://doi.org/10.1016/j.neucom.2016.07.020 Google Scholar
Digital Library
- [48] . 1996. Time-invariant orthonormal wavelet representations. IEEE Transactions on Signal Processing 44, 8 (1996), 1964–1970. https://doi.org/10.1109/78.533717 Google Scholar
Digital Library
- [49] . 1998. Statistical Learning Theory, New York Wiley. Google Scholar
Digital Library
- [50] . 2015. A comparative study of multi-class support vector machine methods for Arabic characters recognition. 2015 IEEE/ACS 12th International Conference of Computer Systems and Applications (AICCSA). 1–6.
DOI: DOI: 10.1109/AICCSA.2015.7507240Google ScholarCross Ref
- [51] . 2009. A new approach for segmentation and recognition of Arabic handwritten touching numeral pairs. International Conference on Computer Analysis of Images and Patterns. Springer, 165–172. https://doi.org/10.1007/978-3-642-03767-2_20. Google Scholar
Digital Library
- [52] . 2009. Using modified contour features and SVM based classifier for the recognition of Persian/Arabic handwritten numerals. 2009 Seventh International Conference on Advances in Pattern Recognition. IEEE, 391–394.
DOI: DOI: 10.1109/ICAPR.2009.14 Google ScholarDigital Library
- [53] . 2014. Handwritten digit recognition based on DCT features and SVM classifier. 2014 Second World Conference on Complex Systems (WCCS). IEEE, 13–16.
DOI: DOI: 10.1109/ICoCS.2014.7060935Google ScholarCross Ref
- [54] . 2009. Automatic recognition of off-line handwritten Arabic (Indian) numerals using support vector and extreme learning machines. International Journal of Imaging 2, (A09) (2009), 34–53.Google Scholar
- [55] . 2012. Handwritten character recognition with artificial neural networks. In Distributed Computing and Artificial Intelligence. Advances in Intelligent and Soft Computing. (eds). Springer, Berlin, 151. https://doi.org/10.1007/978-3-642-28765-7_64Google Scholar
- [56] . 2014. Artificial neural network: A brief overview. In International Journal of Engineering Research and Applications 4, 2 (2014), 07–12.Google Scholar
- [57] . 1944. A method for the solution of certain non-linear problems in least squares. Q. Appl. Math. 2, (1944), 196–168.Google Scholar
Cross Ref
- [58] . 1963. An algorithm for least squares estimation of nonlinear parameters. Journal of the Society for Industrial and Applied Mathematics 11, 2 (1963), 431–-441.Google Scholar
Cross Ref
- [59] . 2016. Assessment of neural network training algorithms for the prediction of polymeric inclusion membranes efficiency. Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi 20, 3 (2016), 533–542.Google Scholar
- [60] . 2005. The least squares problem. Fundam. Matrix Comput. 1989, 181–259.Google Scholar
- [61] . 1992. A practical Bayesian framework for backpropagation networks. Neural Compute 4, 3 (1992), 448–472. Google Scholar
Digital Library
- [62] . 2002. IFN/ENIT-database of handwritten Arabic words. In Proc. of CIFED. CiteSeer, 127–136.Google Scholar
- [63] . 2009. ICDAR 2009 Arabic handwriting recognition competition. 2009 10th International Conference on Document Analysis and Recognition. IEEE, 1383–1387. Google Scholar
Digital Library
Index Terms
Arabic Handwritten Word Recognition Based on Stationary Wavelet Transform Technique using Machine Learning
Recommendations
Signal De-noising in Ultrasonic Testing Based on Stationary Wavelet Transform
GCIS '09: Proceedings of the 2009 WRI Global Congress on Intelligent Systems - Volume 02In ultrasonic testing, the quality of flaw echo-signals is a foundation for locating, quantitative and qualitative analysis. Thus, signal de-noising and increasing of the signal-to-noise ratio (SNR) are a key to successful application of ultrasonic NDT ...
Persian/arabic handwritten word recognition using M-band packet wavelet transform
The extraction of rotation and scale invariant features is an essential problem in document image analysis. This paper proposes an effective rotation and scale invariant holistic handwritten word recognition scheme. This approach utilizes M-band packet ...
Image Resolution Enhancement Using Lifting Wavelet and Stationary Wavelet Transform
ICESC '14: Proceedings of the 2014 International Conference on Electronic Systems, Signal Processing and Computing TechnologiesThis paper presents a technique for enhancing resolution of images by interpolating high frequency sub-bands generated using lifting wavelet transform (LWT) and spatial information of input low resolution (LR) image. Stationary wavelet transform (SWT) ...






Comments