Abstract
The aim of our work is to present a new method based on structural characteristics and a fuzzy classifier for off-line recognition of handwritten Arabic characters in all their forms (beginning, end, middle and isolated). The proposed method can be integrated in any handwritten Arabic words recognition system based on an explicit segmentation process. First, three preprocessing operations are applied on character images: thinning, contour tracing and connected components detection. These operations extract structural characteristics used to divide the set of characters into five subsets. Next, features are extracted using invariant pseudo-Zernike moments. Classification was done using the Fuzzy ARTMAP neural network, which is very fast in training and supports incremental learning. Five Fuzzy ARTMAP neural networks were employed; each one is designed to recognize one subset of characters. The recognition process is achieved in two steps: in the first one, a clustering method affects characters to one of the five character subsets. In the second one, the pseudo-Zernike features are used by the appropriate Fuzzy ARTMAP classifier to identify the character. Training process and tests were performed on a set of character images manually extracted from the IFN/ENIT database. A height recognition rate was reported .
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Abandah GA, Younis KS (2008) Handwritten Arabic character recognition using multiple classifiers based on letter form. In: Proceedings of the 5th conference on signal processing. Pattern recognition application, Innsbruck, Austria, pp 128–133
Abuhaiba I, Mahmoud S, Green R (1994) Recognition of handwritten cursive Arabic characters. IEEE Trans Pattern Anal Mach Intell 16(6):664–672
Aburas AA, Rehiel SMA (2007) Off-line Omni-style handwriting Arabic character recognition system based on wavelet compression. Arab Res Inst Sci Eng 3(4):123–135
Al Abed H, Kherallah M, Margner V, Alimi AM (2010) On-line Arabic handwriting recognition competition, ADAB database and participating systems. Int J Doc Anal Recognit 14(1):15–23
Alabodi J, Li X (2013) An effective approach to off-line Arabic handwriting recognition. Int J Artif Intell Appl 4(6):1–16
Al-Ammar M, Al-Majed R, Aboalsamh H, (2011) On-line handwriting recognition for the Arabic letter set. In: Proceedings of recent researches in communications and information technology conference, Corfu Island, Greece, pp 42–49
Aljuaid H, Mohammed D, Sarfraz M (2011) Evaluation approach of Arabic character recognition. Int J Comput Vis Image Process 1(2):58–77
AlKhateeb JH, Ren J, Jiang J, Al-Muhtaseb H (2011) Off-line handwritten Arabic cursive text recognition using Hidden Markov Models and re-ranking. Pattern Recognit Lett 32(8):1081–1088
Alma’adeed S, Higgens C, Elliman D (2004) Off-line recognition of handwritten Arabic words using multiple hidden Markov models. Knowl Based Syst 17:75–79
Amin A, Murshed N (1999) Recognition of printed Arabic words with Fuzzy ARTMAP neural network. Int Jt Conf Neural Netw 4:2903–2907
Amrouch M, Elyassa M, Rachidi A, Mammass D (2008) Off-line Arabic handwritten characters based on hidden Markov models. In: Proceedings of the 3rd international conference on image and signal processing, Cherbourg-Octeville, France, pp 447–454
Azizi N, Farah N, Khadir MT, Sellami M (2009) Arabic handwritten word recognition using classifiers selection and feature extraction/selection. In: Proceedings of The 17th IEEE conference in intelligent information system, proceedings of recent advances in intelligent information systems, pp 735–742
Ben Amara NE, Boushama F (2003) Classification of Arabic script using multiple sources of information: state of the art and perspectives. Int J Doc Anal Recognit 5(4):195–212
Bhatia AB, Wolf E (1954) On the circle polynomials of Zernike and related orthogonal sets. Proc Camb Philos Soc 50(1):40–48
Bote-Lorenzo M, Dimitriadis Y, Gmez-Snchez E (2002) A hybrid two-stage fuzzy ARTMAP and LVQ neuro-fuzzy system for on-line handwriting recognition. In: Proceedings of the international conference on artificial neural networks, pp 82–82
Bushofa BMF, Spann M (1997) Segmentation and recognition of Arabic characters by structural classification. Image Vis Comput Elsevier 15(4):167–179
Carpenter GA, Grossberg S, Iizuka K (1992) Comparative performance measures of fuzzy ARTMAP, learned vector quantization, and back propagation for handwritten. In: Proceedings of the international joint conference on neural networks, Baltimore, pp 794–799
Carpenter GA, Grossberg S, Markuzon N, Reynolds JH, Rosen DB (1995) A fuzzy ARTMAP non-parametric probability estimator for nonstationary pattern recognition problems. IEEE Trans Neural Netw 6(6):1330–1336
Carpenter GA, Grossberg S, Markuzon N, Reynolds JH, Rosen DB (1992) Fuzzy ARTMAP: a neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Trans Neural Netw 3(5):698–713
Carpenter GA, Grossberg S, Rosen DB (1991) Fuzzy-ART: fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Netw 4:759–771
Dehghan M, Faez K, Ahmadi M, Shridhar M (2001) Handwritten Farsi (Arabic) word recognition: a holistic approach using discrete HMM. Pattern Recognit 34:1057–1065
Freeman JA, Skapura DM (1991) Neural networks algorithms, applications and programming techniques. Addison-Wesley Publishing Company, Boston
Hagan MT, Demuth BH, Beale M (1996) Neural network design. PWS Publishing Company, Boston
Ham FM, Han S (1996) Classification of cardiac arrhythmias using fuzzy ARTMAP. IEEE Trans Biomed Eng 43(4):425–430
Haraty R, Ghaddar C (2004) Arabic text recognition. Int Arab J Inf Technol 1:156–163
Harouni M, Mohamad D, Mohd-Rahim MS, Halawani SM, Afzali M (2012) Handwritten Arabic character recognition based on minimal geometric features. Int J Mach Learn Comput 2(5):578–582
Haykin S (2005) Neural networks: a comprehensive foundation. Pearson Prentice Hall, India
He L, Chao Y, Suzuki K, Wu K (2009) Fast connected-component labelling. Pattern Recognit 42(9):1977–1987
Johnston CT, Bailey DG (2008) FPGA Implementation of a single pass connected components algorithm. In: Proceedigns of the 4th IEEE international symposium on electronic design, test and applications, pp 229–231
Jumari K, Ali MA (2002) A survey and comparative evaluation of selected off-line Arabic handwritten character recognition systems. J Technol 36(4):1–18
Keyarsalan M, Montazer GHA, Kazemi K (2009) Font-Based Persian character recognition using simplified Fuzzy ARTMAP neural network improved by fuzzy sets and particle swarm optimization, IEEE congress on Evolutionary Computing CEC’09, pp 3003–3009
Khedher MZ, Abandah G (2002) Arabic character recognition using approximate stroke sequence. In: Proceedings of the 3rd international conference on language resources and evaluation: workshop on arabic language resources and evaluation: status and prospects, European Language Resources Association, Las Palmas, Canary Islands, Spain, pp 28–34
Khorsheed MS (2007) Off-line recognition of omni-font Arabic text using the HMM toolkit. Pattern Recognit Lett Elsevier Science Inc 28(12):1563–1571
Khotanzad A, Hong YH (1990) Invariant image recognition by Zernike moments. IEEE Trans Pattern Anal Mach Intell 12(5):489–497
Kumar P, Giri SR, Hegde GR, Verma K (2012) A novel algorithm to extract connected components in a binary image of vehicle license plates. IJECCT 2(2):27–32
Lawgali A, Angelova M, Bouridane A (2014) A framework for Arabic handwritten recognition based on segmentation. Int J Hybrid Inf Technol 7(5):413–428
Likforman-Sulem L, Al Hajj Mohammad R, Mokbel C, Menasri F, Bianne-Bernard A-L, Kermorvant C (2012) Features for HMM-based Arabic handwritten word recognition. In: Margner V, El Abed H (eds) Guide to OCR for Arabic Script, Springer, Berlin, pp 123–143
Lim CP, Kuan MM, Harrison RF (2005) Application of fuzzy ARTMAP and fuzzy c-means clustering to pattern classification with incomplete data. Neural Comput Appl 14(2):104–113
Lorigo LM (2006) Off-line Arabic handwriting recognition. IEEE Trans Pattern Anal Mach Intell 28(5):712–727
Maddouri SS, Belaid A, Choisy C, Amiri H (2002) Modèle perceptif neuronal vision globale-locale pour la reconnaissance de mots manuscrits arabes. In: Colloque International Francophone sur l’Écrit et le Document, pp 11–20
Menasri F, Vincent N, Augustin E, Cheriet M (2007) Shape-based alphabet for off-line Arabic handwriting recognition. In: 9th international conference on document analysis and recognition (ICDAR), Volume 2, pp 969–973
Mozaffari S, Faez K, Ziaratban M (2005) Structural decomposition and statistical description of Farsi/Arabic handwritten numeric characters, In: Proceedings of international conference on document analysis and recognition, Seoul, Korea, pp 237–241
Mozaffari S, Soltanizadeh H (2009) ICDAR 2009 handwritten Farsi/Arabic character recognition competition. In: Proceedings of the 10th international conference on document analysis and recognition, Barcelona, Spain, pp 1413–1417
Niya AM, Sajed H (2012) Recognition of individual handwritten letters of the Farsi language using a decision tree. Int J Comput Appl 55(5):7–11
Parrweej F (2012) An empirical evaluation of off-line Arabic handwriting and printed characters recognition system. Int J Comput Sci Issues 9(1):29–35
Pechwitz M, Maddouri SS, Margner V, Ellouze N, Amiri H (2002) IFN/ENIT database of handwritten Arabic words. In: Proceedings of 7ème Colloque International Francophone sur l’Écrit et le Document, Hammamet, Tunis, pp 129–136
Pechwitz M, Margner V, Al Abed H (2006) Comparison of two different feature sets for off-line recognition of handwritten Arabic words. In: Proceedings of international workshop on frontiers in handwriting recognition, La Baule, France, pp 109–114
Pornchaikajornsak A, Thammano A (2003) Handwritten Thai character recognition using fuzzy membership function and fuzzy ARTMAP, the IEEE international symposium on computational intelligence in robotics and automation, pp 40–44
Rachidi A, El Yassa M, Mammass D (2006) A pre-topological approach for handwritten isolated Arabic character recognition. In Proceedings of the second international symposium on communication, control and signal processing, Morocco
Ronsen C, Denjiver PA (1984) Connected components in binary images: the detection problem. Wiley, New York
Sarhan AM, Helalat O (2007) Arabic character recognition using ANN networks and statistical analysis. In: Proceedings of European and mediterranean conference on information systems, Valencia, Spain, pp 2–13
Shanbehzadeh J, Pezashki H, Sarrafzadeh A (2007) Feature extraction from Farsi handwritten letters. In: Proceedings of the 22nd image and vision computing, Waikato University, Hamilton, New Zealand, pp 35–40
Shapiro LG, Stockman GC (2001) Computer vision. Prentice Hall, New Jersey
Slimane F, Kanoun S, Al Abed H, Alimi AM, Ingold R, Hennebert J (2011) Arabic recognition competition: multi-font, multi-size digitally represented text. In: Proceedings of international conference on document analysis and recognition, Beijing, China, pp 1449–1453
Snoussi Maddouri S, Amiri H, Belaid A, Choisy C (2002) Combination of local and global vision modelling for Arabic handwritten words recognition. In: Proceedings of international conference on frontiers in handwriting recognition, pp 128–135
Sternby J, Morwing J, Andersson J, Friberg C (2009) On-line Arabic handwriting recognition with templates. Pattern Recognit Elsevier 42(12):3278–3286
Taherian A, Aliyari SM (2013) Noise resistant identification of human iris patterns using Fuzzy ARTMAP neural network. Int J Secur Appl 7(1):105–118
Tan SC, Lim CP (2011) Fuzzy ARTMAP and hybrid evolutionary programming for pattern classification. J Intell Fuzzy Syst 22(2):57–68
Tay YH, Khalid M, Tan KK, Yusof R (1997) Handwritten postcode recognition by Fuzzy ARTMAP neural network. COSTAM National Science Congress, Genting Highlands
Teh CH, Chin RT (1988) On image analysis by the method of moments. IEEE Trans Pattern Anal Mach Intell 10(4):496–513
Tran MD, Lim CP, Abeynayake C, Jain LC (2010) Feature extraction and classification of metal detector signals using the wavelet transform and the fuzzy ARTMAP neural network. J Intell Fuzzy Syst 21(1):89–99
Vidya V, Indhu TR, Bhadran VK, Ravindra Kumar R (2013) Malayalam off-line handwritten recognition using probabilistic simplified Fuzzy ARTMAP. Intell Inf Adv Intell Syst Comput 182:273–283
Vigdor B, Lerner B (2006) Accurate and fast off and on-line Fuzzy ARTMAP based image classification with application to genetic abnormality diagnosis. IEEE Trans Neural Netw 17(5):1288–1300
Yalniz IZ, Altingovde IS, Güdükbay U, and Ulusoy O (2009) Ottoman archives explorer: a retrieval system for digital Ottoman archives. ACM J Comput Cult Herit, 2(3), Article 8
Zengbing X, Jianping X, Tielin S, Bo W, Youmin H (2009) Application of a modified fuzzy ARTMAP with feature-weight learning for the fault diagnosis of bearing. Expert Syst Appl 36(6):9961–9968
Zhang TY, Suen CY (1984) A fast parallel algorithm for thinning digital patterns. Commun ACM 27(3):236–239
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kef, M., Chergui, L. & Chikhi, S. A novel fuzzy approach for handwritten Arabic character recognition. Pattern Anal Applic 19, 1041–1056 (2016). https://doi.org/10.1007/s10044-015-0500-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-015-0500-4