{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:18:04Z","timestamp":1760242684479,"version":"build-2065373602"},"reference-count":48,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2016,3,11]],"date-time":"2016-03-11T00:00:00Z","timestamp":1457654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Document analysis tasks such as pattern recognition, word spotting or segmentation, require comprehensive databases for training and validation. Not only variations in writing style but also the used list of words is of importance in the case that training samples should reflect the input of a specific area of application. However, generation of training samples is expensive in the sense of manpower and time, particularly if complete text pages including complex ground truth are required. This is why there is a lack of such databases, especially for Arabic, the second most popular language. However, Arabic handwriting recognition involves different preprocessing, segmentation and recognition methods. Each requires particular ground truth or samples to enable optimal training and validation, which are often not covered by the currently available databases. To overcome this issue, we propose a system that synthesizes Arabic handwritten words and text pages and generates corresponding detailed ground truth. We use these syntheses to validate a new, segmentation based system that recognizes handwritten Arabic words. We found that a modification of an Active Shape Model based character classifiers\u2014that we proposed earlier\u2014improves the word recognition accuracy. Further improvements are achieved, by using a vocabulary of the 50,000 most common Arabic words for error correction.<\/jats:p>","DOI":"10.3390\/s16030346","type":"journal-article","created":{"date-parts":[[2016,3,14]],"date-time":"2016-03-14T11:03:45Z","timestamp":1457953425000},"page":"346","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Synthesis of Common Arabic Handwritings to Aid Optical Character Recognition Research"],"prefix":"10.3390","volume":"16","author":[{"given":"Laslo","family":"Dinges","sequence":"first","affiliation":[{"name":"Institute for Information Technology and Communications (IIKT), Otto-von-Guericke-University Magdeburg, D-39016 Magdeburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3632-2402","authenticated-orcid":false,"given":"Ayoub","family":"Al-Hamadi","sequence":"additional","affiliation":[{"name":"Institute for Information Technology and Communications (IIKT), Otto-von-Guericke-University Magdeburg, D-39016 Magdeburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moftah","family":"Elzobi","sequence":"additional","affiliation":[{"name":"Institute for Information Technology and Communications (IIKT), Otto-von-Guericke-University Magdeburg, D-39016 Magdeburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sherif","family":"El-etriby","sequence":"additional","affiliation":[{"name":"Faculty of Computers and Information, Menoufia University-MUFIC, Menoufia 32721, Egypt"},{"name":"Department of Computer, Umm Al-Qura University, Makkah 21421, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2016,3,11]]},"reference":[{"key":"ref_1","unstructured":"Maegner, V., and Abed, H.E. (2008). SACH\u201906: Proceedings of the 2006 Conference on Arabic And Chinese Handwriting Recognition, Springer-Verlag."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.compeleceng.2015.11.030","article-title":"Handwriting recognition of digits, signs, and numerical strings in Persian","volume":"49","author":"Sajedi","year":"2016","journal-title":"Comput. Electr. Eng."},{"key":"ref_3","unstructured":"Abdelaziz, I., and Abdou, S. AltecOnDB: A Large-Vocabulary Arabic Online Handwriting Recognition Database. Available online: http:\/\/arxiv.org\/abs\/1412.7626."},{"key":"ref_4","unstructured":"Elarian, Y., Al-Muhsateb, H.A., and Ghouti, L.M. (2010, January 22). Arabic Handwriting Synthesis. Proceesings of the First International Workshop on Frontiers in Arabic Handwriting Recognition, Istanbul, Turkey."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1016\/j.patcog.2014.09.013","article-title":"An Arabic handwriting synthesis system","volume":"48","author":"Elarian","year":"2015","journal-title":"Pattern Recognit."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/s10032-012-0190-z","article-title":"IESK-ArDB: A database for handwritten Arabic and optimized topological segmentation approach","volume":"16","author":"Elzobi","year":"2013","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1109\/TPAMI.2006.102","article-title":"Offline Arabic Handwriting Recognition: A Survey","volume":"28","author":"Lorigo","year":"2006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1007\/BF00336740","article-title":"An oscillation theory of handwriting","volume":"39","author":"Hollerbach","year":"1981","journal-title":"Biol. Cybernet."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1007\/s10032-007-0046-0","article-title":"An oscillatory neuromotor model of handwriting generation","volume":"10","author":"Gangadhar","year":"2007","journal-title":"IJDAR"},{"key":"ref_10","unstructured":"Plamondon, R., and Guerfali, W. (1996). The Generation of Handwriting with Delta-lognormal Synergies, Laboratoire Scribens, D\u00e9partement de g\u00e9nie \u00c9lectrique et de G\u00e9nie Informatique, \u00c9cole Polytechnique de Montr\u00e9al. Rapport Technique."},{"key":"ref_11","unstructured":"Guyon, I. Handwriting Synthesis From Handwritten Glyphs. Available online: http:\/\/citeseerx.ist.psu. edu\/viewdoc\/summary?doi=10.1.1.33.1962."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Khader, A., Saudagar, J., and Mohammed, H.V. (2015, January 24\u201326). Concatenation Technique for Extracted Arabic Characters for Efficient Content-based Indexing and Searching. Proceedings of the Second International Conference on Computer and Communication Technologies, Advances in Intelligent Systems and Computing, Hyderabad, India.","DOI":"10.1007\/978-81-322-2517-1_55"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Marinai, S., and Fujisawa, H. (2008). Machine Learning in Document Analysis and Recognition, Springer.","DOI":"10.1007\/978-3-540-76280-5"},{"key":"ref_14","unstructured":"Zheng, Y., and Doermann, D.S. (September, January 29). Handwriting Matching and Its Application to Handwriting Synthesis. Proceedings of the Eighth International Conference on Document Analysis and Recognition (ICDAR 2005), Seoul, Korea."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1016\/j.patcog.2004.10.007","article-title":"Overlap pattern synthesis with an efficient nearest neighbor classifier","volume":"38","author":"Viswanath","year":"2005","journal-title":"Pattern Recognit."},{"key":"ref_16","unstructured":"Choi, H.I., Cho, S.J., and Kim, J.H. (2003). Generation of Handwritten Characters with Bayesian network based On-line Handwriting Recognizers. ICDAR."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Dolinsky, J., and Takagi, H. (2007, January 19\u201321). Synthesizing handwritten characters using naturalness learning. Proceedings of the IEEE International Conferenceon Computational Cybernetics (ICCC), Gammarth, Tunisia.","DOI":"10.1109\/ICCCYB.2007.4402023"},{"key":"ref_18","unstructured":"Al-Zubi, S. (2004). Active Shape Structural Model. [Ph.D. Thesis, Otto-von-Guericke-University Magdeburg]."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1109\/TPAMI.2003.1177158","article-title":"Handwritten Chinese Radical Recognition Using Nonlinear Active Shape Models","volume":"25","author":"Shi","year":"2003","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/978-3-540-44871-6_39","article-title":"Generation and use of synthetic training data in cursive handwriting recognition","volume":"Volume 2652","author":"Perales","year":"2003","journal-title":"Pattern Recognition and Image Analysis"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1445","DOI":"10.1016\/j.patcog.2008.08.017","article-title":"Retrieval of Online Handwriting by Synthesis and Matching","volume":"42","author":"Jawahar","year":"2009","journal-title":"Pattern Recognit."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Rao, P. (1993). Shape Vectors: An Efficient Parametric Representation for the Synthesis and Recognition of Hand Script Characters, Saddhana.","DOI":"10.1007\/BF02811383"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2097","DOI":"10.1016\/j.patcog.2006.11.024","article-title":"Style-preserving English Handwriting Synthesis","volume":"40","author":"Lin","year":"2007","journal-title":"Pattern Recognit."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1007\/s10032-004-0131-6","article-title":"Combining Shape and Physical Models for On-Line Cursive Handwriting Synthesis","volume":"7","author":"Wang","year":"2003","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3365","DOI":"10.1016\/j.patcog.2008.12.018","article-title":"Synthetic handwritten CAPTCHAs","volume":"42","author":"Thomas","year":"2009","journal-title":"Pattern Recognit."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Gaur, S., Sonkar, S., and Roy, P.P. (2015, January 23\u201326). Generation of synthetic training data for handwritten Indic script recognition. Proceedings of the 13th International Conference on Document Analysis and Recognition, Tunis, Tunisia.","DOI":"10.1109\/ICDAR.2015.7333810"},{"key":"ref_27","unstructured":"Xu, Y., Shum, H., Wang, J., and Wu, C. (2007). Learning-Based System and Process for Synthesizing Cursive Handwriting. (7,227,993), U.S. Patent."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Saabni, R.M., and El-Sana, J.A. (2012). Comprehensive Synthetic Arabic Database for On\/off-Line Script Recognition Research, Springer-Verlag.","DOI":"10.1007\/s10032-012-0189-5"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"323575","DOI":"10.1155\/2015\/323575","article-title":"ASM based Synthesis of Handwritten Arabic Text Pages","volume":"2015","author":"Dinges","year":"2015","journal-title":"Sci. World J."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"10942","DOI":"10.1016\/j.eswa.2009.02.024","article-title":"HAH manuscripts: A holistic paradigm for classifying and retrieving historical Arabic handwritten documents","volume":"36","author":"Aghbari","year":"2009","journal-title":"Expert Syst. Appl."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1007\/s100320050040","article-title":"Off-Line Cursive Script Word Recognition\u2014A Survey","volume":"2","author":"Steinherz","year":"1999","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"ref_32","first-page":"304","article-title":"Handwriting Arabic character recognition LeNet using neural network","volume":"6","year":"2009","journal-title":"Int. Arab. J. Inf. Technol."},{"key":"ref_33","unstructured":"Ding, X., and Liu, H. (2006, January 27\u201328). Segmentation-driven offline handwritten Chinese and Arabic script recognition. Proceedings of the 2006 Conference on Arabic and Chinese Handwriting Recognition, College Park, MD, USA."},{"key":"ref_34","first-page":"352","article-title":"Implicit Vs Explicit based Script Segmentation and Recognition: A Performance Comparison on Benchmark Database","volume":"2","author":"Rehman","year":"2009","journal-title":"Int. J. Open Problems Compt. Math."},{"key":"ref_35","first-page":"11","article-title":"Segmentation of Arabic Text into Characters for Recognition","volume":"20","author":"Shaik","year":"2008","journal-title":"IMTIC"},{"key":"ref_36","unstructured":"Lorigo, L., and Govindaraju, V. (September, January 29). Segmentation and Pre-Recognition of Arabic Handwriting. Proceedings of the Eighth International Conference on Document Analysis and Recognition (ICDAR\u201905), Seoul, Korea."},{"key":"ref_37","unstructured":"Shanbehzadeh, J., Pezashki, H., and Sarrafzadeh, A. Features Extraction from Farsi Hand Written Letters. Available online: http:\/\/digital.liby.waikato.ac.nz\/conferences\/ivcnz07\/papers\/ivcnz07-paper7.pdf."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"3721","DOI":"10.1016\/j.patcog.2007.03.014","article-title":"A SVM-based cursive character recognizer","volume":"40","author":"Camastra","year":"2007","journal-title":"Pattern Recognit."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Oneto, L., Ridella, S., and Anguita, D. (2015). Tikhonov, Ivanov and Morozov Regularization for Support Vector Machine Learning. Mach. Learn.","DOI":"10.1007\/s10994-015-5540-x"},{"key":"ref_40","unstructured":"Parkins, A.D., and Nandi, A.K. (2002, January 3\u20136). Simplifying Hand Written Digit Recognition Using a Genetic Algorithm. Proceedings of the 11th European Signal Processing Conference, Toulouse, France."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1504\/IJCVR.2015.072193","article-title":"SIFT descriptors for Arabic handwriting recognition","volume":"5","author":"Chergui","year":"2015","journal-title":"Int. J. Comput. Vis. Robot."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"18209","DOI":"10.3390\/s150818209","article-title":"Distance-Constraint k-Nearest Neighbor Searching in Mobile Sensor Networks","volume":"15","author":"Han","year":"2015","journal-title":"Sensors"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"844","DOI":"10.1002\/int.20496","article-title":"Efficient KNN search by linear projection of image clusters","volume":"26","author":"Aghbari","year":"2011","journal-title":"Int. J. Intell. Syst."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"14241","DOI":"10.3390\/s150614241","article-title":"Acoustic Biometric System Based on Preprocessing Techniques and Linear Support Vector Machines","volume":"15","author":"Villacorta","year":"2015","journal-title":"Sensors"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Cire\u015fan, D., Meier, U., and Schmidhuber, J. (2012, January 16\u201321). Multi-column Deep Neural Networks for Image Classification. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1145\/146370.146380","article-title":"Techniques for Automatically Correcting Words in Text","volume":"24","author":"Kukich","year":"1992","journal-title":"ACM Comput. Surv."},{"key":"ref_47","unstructured":"Wordfreq. Available online: https:\/\/github.com\/zacharydenton\/zaum\/blob\/master\/ public\/data\/ wordfreq\/ar\/ar_50K.txt."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Dinges, L., Al-Hamadi, A., and Elzobi, M. (2012, January 21\u201325). An Active Shape Model based approach for Arabic Handwritten Character Recognition. Proceedings of the 11th International Conference on Signal Processing, Beijing, China.","DOI":"10.1109\/ICoSP.2012.6491790"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/16\/3\/346\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T19:20:36Z","timestamp":1760210436000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/16\/3\/346"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3,11]]},"references-count":48,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2016,3]]}},"alternative-id":["s16030346"],"URL":"https:\/\/doi.org\/10.3390\/s16030346","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2016,3,11]]}}}