Deep Learning Algorithms for Arabic Handwriting Recognition: A Review

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


     Computer vision (CV) refers to the study of the computer simulation of human visual science. Major task of CV is to collect images (or video) so that they could be used for analysis, gathering information, and making decisions or judgements. CV has greatly progressed and developed in the past few decades. In recent years, deep learning (DL) approaches have won several contests in pattern recognition and machine learning. (DL) dramatically improved the state-of-the-art in visual object recognition, object detection, handwritten recognition and many other domains. Handwritten recognition technique is one of this tasks that targeted to extract the text from documents or another images type. In contrast to the English domain, there are a limited works on the Arabic language that achieved satisfactory results, Due to the Arabic language cursive nature that induces many technical difficulties. This paper highlighted the pre-processing and binarization methods that have been used in the literature along with proposed numerous directions for developing. We review the various current deep learning approaches and tools used for Arabic handwritten recognition (AHWR), identified challenges along this line of this research, and gives several recommendations including a framework based (DL) that is particularly applicable for dealing with cursive nature languages.


     


  • Keywords


    Arabic OCR; Deep Convolutional Neural Networks; pattern recognition; image processing, Text recognition.

  • References


      [1] Porwal, U., Y. Zhou, and V. Govindaraju. Handwritten arabic text recognition using deep belief networks. in Pattern Recognition (ICPR), 2012 21st International Conference on. 2012. IEEE.

      [2] Tamen, Z., H. Drias, and D. Boughaci, An efficient multiple classifier system for Arabic handwritten words recognition. Pattern Recognition Letters, 2017.

      [3] Ashiquzzaman, A. and A.K. Tushar. Handwritten Arabic numeral recognition using deep learning neural networks. in Imaging, Vision & Pattern Recognition (icIVPR), 2017 IEEE International Conference on. 2017. IEEE.

      [4] Rabi, M., et al. Recognition of cursive Arabic handwritten text using embedded training based on HMMs. in Engineering & MIS (ICEMIS), International Conference on. 2016. IEEE.

      [5] Dalal, N., et al., Histograms of oriented gradients for human detection. Computer Vision and Pattern Recognition CVPR Society Conference on, 2005. 1 SRC - GoogleScholar: p. 886-893.

      [6] Elleuch, M., R. Mokni, and M. Kherallah. Offline Arabic Handwritten recognition system with dropout applied in Deep networks based-SVMs. in Neural Networks (IJCNN), 2016 International Joint Conference on. 2016. IEEE.

      [7] Lowe, D.G., Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004. 60(2 SRC - GoogleScholar): p. 91-110.

      [8] Elleuch, M., R. Maalej, and M. Kherallah, A New Design Based-SVM of the CNN Classifier Architecture with Dropout for Offline Arabic Handwritten Recognition. Procedia Computer Science, 2016. 80: p. 1712-1723.

      [9] Elleuch, M., N. Tagougui, and M. Kherallah, Optimization of DBN using Regularization Methods Applied for Recognizing Arabic Handwritten Script. Procedia Computer Science, 2017. 108: p. 2292-2297.

      [10] Ahmad, I., S.A. Mahmoud, and G.A. Fink, Open-vocabulary recognition of machine-printed Arabic text using hidden Markov models. Pattern Recognition, 2016. 51: p. 97-111.

      [11] Hafiz, A.M. and G.M. Bhat, Arabic OCR Using a Novel Hybrid Classification Scheme. Journal of Pattern Recognition Research, 2016. 1: p. 55-60.

      [12] Azeem, S.A. and H. Ahmed, Effective technique for the recognition of offline Arabic handwritten words using hidden Markov models. International Journal on Document Analysis and Recognition (IJDAR), 2013. 16(4): p. 399-412.

      [13] Álvaro, F., J.-A. Sánchez, and J.-M. Benedí, Recognition of on-line handwritten mathematical expressions using 2D stochastic context-free grammars and hidden Markov models. Pattern Recognition Letters, 2014. 35: p. 58-67.

      [14] Jayech, K., M.A. Mahjoub, and N.E.B. Amara, Synchronous Multi-Stream Hidden Markov Model for offline Arabic handwriting recognition without explicit segmentation. Neurocomputing, 2016. 214 : p. 958-971.

      [15] Lawgali, A., A survey on arabic character recognition. International Journal of Signal Processing, Image Processing and Pattern Recognition, 2015. 8(2): p. 401-426.

      [16] Amrouch, M. and M. Rabi. Deep Neural Networks Features for Arabic Handwriting Recognition. in International Conference on Advanced Information Technology, Services and Systems. 2017. Springer.

      [17] Rani, S. and G.S. Lehal. Recognition based classification of Gurmukhi manuscripts. in Colossal Data Analysis and Networking (CDAN), Symposium on. 2016. IEEE.

      [18] 18. Naz, S., et al. Challenges in baseline detection of cursive script languages. in Science and Information Conference (SAI), 2013. 2013. IEEE.

      [19] Borovikov, E. and I. Zavorin, A multi-stage approach to Arabic document analysis, in Guide to OCR for Arabic scripts. 2012, Springer. p. 55-78.

      [20] Shafait, F. and T.M. Breuel. A simple and effective approach for border noise removal from document images. in Multitopic Conference, 2009. INMIC 2009. IEEE 13th International. 2009. IEEE.

      [21] Stamatopoulos, N., B. Gatos, and T. Georgiou. Page frame detection for double page document images. in Proceedings of the 9th IAPR International Workshop on Document Analysis Systems. 2010. ACM.

      [22] Chen, K., et al. Page segmentation for historical handwritten document images using color and texture features. in Frontiers in Handwriting Recognition (ICFHR), 2014 14th International Conference on. 2014. IEEE.

      [23] Chakraborty, A. and M. Blumenstein. Preserving Text Content from Historical Handwritten Documents. in Document Analysis Systems (DAS), 2016 12th IAPR Workshop on. 2016. IEEE.

      [24] Farahmand, A., A. Sarrafzadeh, and J. Shanbehzadeh, Document image noises and removal methods. 2013.

      [25] Naz, S., et al., Segmentation techniques for recognition of Arabic-like scripts: A comprehensive survey. Education and Information Technologies, 2016. 21(5): p. 1225-1241.

      [26] Nagy, G., S. Seth, and M. Viswanathan, A prototype document image analysis system for technical journals. Computer, 1992. 25(7): p. 10-22.

      [27] Pavlidis, T. and J. Zhou, Page segmentation and classification. CVGIP: Graphical models and image processing, 1992. 54(6): p. 484-496.

      [28] Wang, D. and S.N. Srihari, Classification of newspaper image blocks using texture analysis. Computer Vision, Graphics, and Image Processing, 1989. 47(3): p. 327-352.

      [29] O'Gorman, L., The document spectrum for page layout analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993. 15(11): p. 1162-1173.

      [30] Wong, K.Y., R.G. Casey, and F.M. Wahl, Document analysis system. IBM journal of research and development, 1982. 26(6): p. 647-656.

      [31] Baird, H.S., Background structure in document images. International Journal of Pattern Recognition and Artificial Intelligence, 1994. 8(05): p. 1013-1030.

      [32] Breuel, T.M. Two geometric algorithms for layout analysis. in International workshop on document analysis systems. 2002. Springer.

      [33] Kise, K., A. Sato, and M. Iwata, Segmentation of page images using the area Voronoi diagram. Computer Vision and Image Understanding, 1998. 70(3): p. 370-382.

      [34] Jelodar, M.S., et al. A Persian OCR System Using Morphological Operators. in WEC (2). 2005.

      [35] Bukhari, S.S., F. Shafait, and T.M. Breuel, Layout analysis of Arabic script documents, in Guide to OCR for Arabic scripts. 2012, Springer. p. 35-53.

      [36] Otsu, N., A threshold selection method from gray-level histograms. Automatica, 1975. 11(285-296): p. 23-27.

      [37] Sauvola, J. and M. Pietikäinen, Adaptive document image binarization. Pattern recognition, 2000. 33(2): p. 225-236.

      [38] El Moubtahij, H., A. Halli, and K. Satori, HMM Off-line Arabic Handwriting Recognition Using the Components of the Frame Binary Intensity, its Grayscale Transform and its Horizontal and Vertical Derivatives. International Journal of Imaging and Robotics™, 2016. 16(2): p. 78-90.

      [39] Kef, M., L. Chergui, and S. Chikhi, A novel fuzzy approach for handwritten Arabic character recognition. Pattern Analysis and Applications, 2016. 19(4): p. 1041-1056.

      [40] Naz, S., et al., The optical character recognition of Urdu-like cursive scripts. Pattern Recognition, 2014. 47(3): p. 1229-1248.

      [41] Saberi, A., et al., Evaluating the legibility of decorative arabic scripts for Sultan Alauddin mosque using an enhanced soft-computing hybrid algorithm. Computers in Human Behavior, 2016. 55: p. 127-144.

      [42] Su, B., S. Lu, and C.L. Tan. Binarization of historical document images using the local maximum and minimum. in Proceedings of the 9th IAPR International Workshop on Document Analysis Systems. 2010. ACM.

      [43] Su, B., S. Lu, and C.L. Tan, Robust document image binarization technique for degraded document images. IEEE transactions on image processing, 2013. 22(4): p. 1408-1417.

      [44] Chen, Y. and L. Wang, Broken and Degraded Document Images Binarization. Neurocomputing, 2017.

      [45] Agrawal, M. and D. Doermann. Clutter noise removal in binary document images. in 2009 10th International Conference on Document Analysis and Recognition. 2009. IEEE.

      [46] Agrawal, M. and D. Doermann, Clutter noise removal in binary document images. International Journal on Document Analysis and Recognition (IJDAR), 2013. 16(4): p. 351-369.

      [47] Toh, K.K.V., N.A.M. Isa, and N. Ashidi, Noise adaptive fuzzy switching median filter for salt-and-pepper noise reduction. IEEE signal processing letters, 2010. 17(3): p. 281-284.

      [48] Chinnasarn, K., Y. Rangsanseri, and P. Thitimajshima. Removing salt-and-pepper noise in text/graphics images. in Circuits and Systems, 1998. IEEE APCCAS 1998. The 1998 IEEE Asia-Pacific Conference on. 1998. IEEE.

      [49] Lee, W.-L. and K.-C. Fan, Document image preprocessing based on optimal Boolean filters. Signal processing, 2000. 80(1): p. 45-55.

      [50] Ping, Z. and C. Lihui, Document filters using morphological and geometrical features of characters. Image and Vision Computing, 2001. 19(12): p. 847-855.

      [51] Bataineh, B., S.N.H.S. Abdullah, and K. Omar, Adaptive binarization method for degraded document images based on surface contrast variation. Pattern Analysis and Applications, 2017. 20(3): p. 639-652.

      [52] Hadjadj, Z., et al., A new efficient binarization method: application to degraded historical document images. Signal, Image and Video Processing, 2017: p. 1-8.

      [53] Jino, P. and K. Balakrishnan. Combined approach for binarization of offline handwritten documents. in Electronics and Communication Systems (ICECS), 2017 4th International Conference on. 2017. IEEE.

      [54] Kashef, S., H. Nezamabadi-pour, and E. Rashedi, Adaptive enhancement and binarization techniques for degraded plate images. Multimedia Tools and Applications, 2017: p. 1-17.

      [55] Lu, D., et al. Binarization of degraded document image based on contrast enhancement. in Control Conference (CCC), 2016 35th Chinese. 2016. IEEE.

      [56] Najafi, M.H. and M.E. Salehi, A fast fault-tolerant architecture for sauvola local image thresholding algorithm using stochastic computing. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2016. 24(2): p. 808-812.

      [57] Kapur, J.N., P.K. Sahoo, and A.K. Wong, A new method for gray-level picture thresholding using the entropy of the histogram. Computer vision, graphics, and image processing, 1985. 29(3): p. 273-285.

      [58] Kittler, J. and J. Illingworth, Minimum error thresholding. Pattern recognition, 1986. 19(1): p. 41-47.

      [59] Ntirogiannis, K., B. Gatos, and I. Pratikakis, Performance evaluation methodology for historical document image binarization. IEEE Transactions on Image Processing, 2013. 22(2): p. 595-609.

      [60] Liu, M., et al., Genetic algorithm and mathematical morphology based binarization method for strip steel defect image with non-uniform illumination. Journal of Visual Communication and Image Representation, 2016. 37: p. 70-77.

      [61] Hassanien, A.E., et al. Historic handwritten manuscript binarisation using whale optimisation. in Systems, Man, and Cybernetics (SMC), 2016 IEEE International Conference on. 2016. IEEE.

      [62] Singh, B.M., et al., Adaptive binarization of severely degraded and non-uniformly illuminated documents. International Journal on Document Analysis and Recognition (IJDAR), 2014. 17(4): p. 393-412.

      [63] Wen, J., S. Li, and J. Sun, A new binarization method for non-uniform illuminated document images. Pattern recognition, 2013. 46(6): p. 1670-1690.

      [64] Guo, Y., et al., Deep learning for visual understanding: A review. Neurocomputing, 2016. 187: p. 27-48.

      [65] Ahmed, R., W.G. Al-Khatib, and S. Mahmoud, A survey on handwritten documents word spotting. International Journal of Multimedia Information Retrieval, 2017. 6(1): p. 31-47.

      [66] Elleuch, M., N. Tagougui, and M. Kherallah, A novel architecture of CNN based on SVM classifier for recognising Arabic handwritten script. International Journal of Intelligent Systems Technologies and Applications, 2016. 15(4): p. 323-340.

      [67] Hafemann, L.G., R. Sabourin, and L.S. Oliveira, Learning features for offline handwritten signature verification using deep convolutional neural networks. Pattern Recognition, 2017. 70: p. 163-176.

      [68] Jin, L., et al., Online Handwritten Chinese Character Recognition: From a Bayesian Approach to Deep Learning, in Advances in Chinese Document and Text Processing. 2017, World Scientific. p. 79-126.

      [69] Poznanski, A. and L. Wolf. Cnn-n-gram for handwriting word recognition. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016.

      [70] Sheng, F., et al. End-to-End Chinese Image Text Recognition with Attention Model. in International Conference on Neural Information Processing. 2017. Springer.

      [71] Chen, L., et al. Cascading Training for Relaxation CNN on Handwritten Character Recognition. in Frontiers in Handwriting Recognition (ICFHR), 2016 15th International Conference on. 2016. IEEE.

      [72] Xiao, X., et al., Design of a Very Compact CNN Classifier for Online Handwritten Chinese Character Recognition Using DropWeight and Global Pooling. arXiv preprint arXiv:1705.05207, 2017.

      [73] Amrouch, M. and M. Rabi, The Relevant CNNs Features Based HMM for Arabic Handwriting Recognition. International Journal of Imaging and Robotics™, 2017. 17(3): p. 98-109.

      [74] Maitra, D.S., U. Bhattacharya, and S.K. Parui. CNN based common approach to handwritten character recognition of multiple scripts. in Document Analysis and Recognition (ICDAR), 2015 13th International Conference on. 2015. IEEE.

      [75] Sun, Y. and Q. Liu, Attribute Recognition from Clothing Using a Faster R-CNN based Multi-task Network. International Journal of Wavelets, Multiresolution and Information Processing, 2018.

      [76] Wu, C., et al. Handwritten character recognition by alternately trained relaxation convolutional neural network. in Frontiers in Handwriting Recognition (ICFHR), 2014 14th International Conference on. 2014. IEEE.

      [77] Xiao, X., et al., Building Fast and Compact Convolutional Neural Networks for Offline Handwritten Chinese Character Recognition. arXiv preprint arXiv:1702.07975, 2017.

      [78] Zhong, Z., L. Jin, and Z. Xie. High performance offline handwritten chinese character recognition using googlenet and directional feature maps. in Document Analysis and Recognition (ICDAR), 2015 13th International Conference on. 2015. IEEE.


 

View

Download

Article ID: 19271
 
DOI: 10.14419/ijet.v7i3.20.19271




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.