{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T17:47:42Z","timestamp":1762624062717,"version":"build-2065373602"},"reference-count":47,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2018,8,24]],"date-time":"2018-08-24T00:00:00Z","timestamp":1535068800000},"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>The majority of handwritten word recognition strategies are constructed on learning-based generative frameworks from letter or word training samples. Theoretically, constructing recognition models through discriminative learning should be the more effective alternative. The primary goal of this research is to compare the performances of discriminative and generative recognition strategies, which are described by generatively-trained hidden Markov modeling (HMM), discriminatively-trained conditional random fields (CRF) and discriminatively-trained hidden-state CRF (HCRF). With learning samples obtained from two dissimilar databases, we initially trained and applied an HMM classification scheme. To enable HMM classifiers to effectively reject incorrect and out-of-vocabulary segmentation, we enhance the models with adaptive threshold schemes. Aside from proposing such schemes for HMM classifiers, this research introduces CRF and HCRF classifiers in the recognition of offline Arabic handwritten words. Furthermore, the efficiencies of all three strategies are fully assessed using two dissimilar databases. Recognition outcomes for both words and letters are presented, with the pros and cons of each strategy emphasized.<\/jats:p>","DOI":"10.3390\/s18092786","type":"journal-article","created":{"date-parts":[[2018,8,24]],"date-time":"2018-08-24T11:13:45Z","timestamp":1535109225000},"page":"2786","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Generative vs. Discriminative Recognition Models for Off-Line Arabic Handwriting"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4074-6440","authenticated-orcid":false,"given":"Moftah","family":"Elzobi","sequence":"first","affiliation":[{"name":"Institute for Information Technology and Communications (IIKT), Otto von Guericke University, 39106 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, 39106 Magdeburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2018,8,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A., and Hinton, G.E. (2013, January 26\u201331). Speech recognition with deep recurrent neural networks. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada.","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Elzobi, M., Al-Hamadi, A., Al Aghbari, Z., and Dings, L. (2012). IESK-ArDB: A database for handwritten Arabic and an optimized topological segmentation approach. Int. J. Doc. Anal. Recognit., 1\u201314.","DOI":"10.1007\/s10032-012-0190-z"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Elzobi, M., Al-Hamadi, A., Dings, L., Elmezain, M., and Saeed, A. (2013, January 25\u201328). A Hidden Markov Model-Based Approach with an Adaptive Threshold Model for Off-Line Arabic Handwriting Recognition. Proceedings of the 2013 12th International Conference on Document Analysis and Recognition 2013, Washington, DC, USA.","DOI":"10.1109\/ICDAR.2013.192"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1561\/2200000013","article-title":"An Introduction to Conditional Random Fields","volume":"4","author":"Sutton","year":"2012","journal-title":"Found. Trends Mach. Learn."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"23:1","DOI":"10.1145\/2431211.2431222","article-title":"Offline arabic handwritten text recognition: A Survey","volume":"45","author":"Parvez","year":"2013","journal-title":"ACM Comput. Surv."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/s10032-009-0098-4","article-title":"Markov models for offline handwriting recognition: A survey","volume":"12","author":"Ploetz","year":"2009","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":"1057","DOI":"10.1016\/S0031-3203(00)00051-0","article-title":"Handwritten Farsi (Arabic) word recognition: A holistic approach using discrete HMM","volume":"34","author":"Dehghan","year":"2001","journal-title":"Pattern Recognit."},{"key":"ref_9","unstructured":"Pechwitz, M., and Maergner, V. (2003, January 6). HMM based approach for handwritten arabic word recognition using the IFN\/ENIT\u2014Database. Proceedings of the Seventh International Conference on Document Analysis and Recognition, Edinburgh, UK."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1165","DOI":"10.1109\/TPAMI.2008.136","article-title":"Combining Slanted-Frame Classifiers for Improved HMM-Based Arabic Handwriting Recognition","volume":"31","author":"Mokbel","year":"2009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/s10032-011-0160-x","article-title":"Confidence- and margin-based MMI\/MPE discriminative training for offline handwriting recognition","volume":"14","author":"Dreuw","year":"2011","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ahmad, I., and Fink, G.A. (2016, January 23\u201326). Class-Based Contextual Modeling for Handwritten Arabic Text Recognition. Proceedings of the 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), Shenzhen, China.","DOI":"10.1109\/ICFHR.2016.0107"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Elzobi, M., Al-Hamadi, A., Dings, L., and El-Etriby, S. (2015, January 14\u201316). CRF and HCRF Based Recognition for Off-Line Arabic Handwriting. Proceedings of the 11th International Symposium on Advances in Visual Computing, Las Vegas, NV, USA.","DOI":"10.1007\/978-3-319-27863-6_31"},{"key":"ref_14","unstructured":"Feng, S., Manmatha, R., and Mccallum, A. (2006, January 27\u201329). Exploring the Use of Conditional Random Field Models and HMM for Historical Handwritten Document Recognition. Proceedings of the 2nd IEEE International Conference on Document Image Analysis for Libraries (DIAL), Lyon, France."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Hamdani, M., Shaik, M.A.B., Doetsch, P., and Ney, H. (2015, January 23\u201326). Investigation of Segmental Conditional Random Fields for large vocabulary handwriting recognition. Proceedings of the 2015 13th International Conference on Document Analysis and Recognition (ICDAR), Tunis, Tunisia.","DOI":"10.1109\/ICDAR.2015.7333764"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Chen, G., Li, Y., and Srihari, S.N. (arXiv, 2016). Word Recognition with Deep Conditional Random Fields, arXiv.","DOI":"10.1109\/ICIP.2016.7532694"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2413","DOI":"10.1109\/TPAMI.2013.49","article-title":"Handwritten Chinese\/Japanese Text Recognition Using Semi-Markov Conditional Random Fields","volume":"35","author":"Zhou","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_18","unstructured":"Gonzalez, R.C., and Woods, R.E. (1992). Digital Image Processing, Addison-Wesley."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Cheriet, M., Kharma, N., Liu, C.L., and Suen, C. (2007). Character Recognition Systems: A Guide for Students and Practitioners, Wiley-Interscience.","DOI":"10.1002\/9780470176535"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Maergner, V., and El Abed, H. (2012). Features for HMM-Based Arabic Handwritten Word Recognition Systems. Guide to OCR for Arabic Scripts, Springer.","DOI":"10.1007\/978-1-4471-4072-6"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1109\/34.993558","article-title":"Shape matching and object recognition using shape contexts","volume":"24","author":"Belongie","year":"2002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1832","DOI":"10.1109\/TPAMI.2005.220","article-title":"Efficient shape matching using shape contexts","volume":"27","author":"Mori","year":"2005","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"013016","DOI":"10.1117\/1.JEI.22.1.013016","article-title":"Keywords image retrieval in historical handwritten Arabic documents","volume":"22","author":"Saabni","year":"2013","journal-title":"J. Electron. Imaging"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1016\/S0031-3203(03)00224-3","article-title":"Handwritten digit recognition: Investigation of normalization and feature extraction techniques","volume":"37","author":"Liu","year":"2004","journal-title":"Pattern Recognit."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Yu, J., and Jia, C. (2009, January 12\u201314). Initializing K-means Clustering Using Affinity Propagation. Proceedings of the Ninth International Conference on Hybrid Intelligent Systems, Shenyang, China.","DOI":"10.1109\/HIS.2009.73"},{"key":"ref_26","unstructured":"Dueck, D. (2009). Affinity Propagation: Clustering Data by Passing Messages, University of Toronto."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Geiger, J., Schenk, J., Wallhoff, F., and Rigoll, G. (2010, January 16\u201318). Optimizing the Number of States for HMM-Based On-line Handwritten Whiteboard Recognition. Proceedings of the 2010 International Conference on Frontiers in Handwriting Recognition (ICFHR), Kolkata, India.","DOI":"10.1109\/ICFHR.2010.23"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zimmermann, M., and Bunke, H. (2002). Hidden Markov Model Length Optimization for Handwriting Recognition Systems. Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR\u201902), IEEE Computer Society.","DOI":"10.1109\/IWFHR.2002.1030938"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Elmezain, M., Al-Hamadi, A., Appenrodt, J., and Michaelis, B. (2008, January 8\u201311). A Hidden Markov Model-based continuous gesture recognition system for hand motion trajectory. Proceedings of the 19th International Conference on Pattern Recognition, Tampa, FL, USA.","DOI":"10.1109\/ICPR.2008.4761080"},{"key":"ref_30","unstructured":"Al-Ohali, Y., Cheriet, M., and Suen, C. (2002, January 11\u201315). Introducing termination probabilities to HMM. Proceedings of the 16th International Conference on Pattern Recognition, Quebec, QC, Canada."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","article-title":"A tutorial on hidden Markov models and selected applications in speech recognition","volume":"77","author":"Rabiner","year":"1989","journal-title":"Proc. IEEE"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Elmezain, M., Hamadi, A., and Michaelis, B. (2010). Hand Gesture Spotting and Recognition Using HMM and CRF in Color Image Sequences. [Ph.D. Thesis, Otto-von-Guericke-Universitaet].","DOI":"10.1109\/ICIP.2009.5414322"},{"key":"ref_33","unstructured":"Willett, D., Worm, A., Neukirchen, C., and Rigoll, G. (December, January 30). Confidence Measures For HMM-Based Speech Recognition. Proceedings of the 5th International Conference on Spoken Language Processing (ICSLP 98), Sydney, Australia."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1109\/34.799904","article-title":"An HMM-based threshold model approach for gesture recognition","volume":"21","author":"Lee","year":"1999","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1109\/34.291449","article-title":"Off-line handwritten word recognition using a hidden Markov model type stochastic network","volume":"16","author":"Chen","year":"1994","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_36","unstructured":"Wikipedia (2015, January 06). Word Error Rate\u2014Wikipedia, The Free Encyclopedia, 2014. Available online: https:\/\/en.wikipedia.org\/wiki\/Word_error_rate."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Sminchisescu, C., Kanaujia, A., Li, Z., and Metaxas, D. (2005, January 17\u201321). Conditional models for contextual human motion recognition. Proceedings of the Tenth IEEE International Conference on Computer Vision, Beijing, China.","DOI":"10.1109\/ICCV.2005.59"},{"key":"ref_38","unstructured":"Lafferty, J. (USA 2001). Conditional Random Fields: Probabilistic Models for Segmenting And Labeling Sequence Data, Morgan Kaufmann."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1007\/BF01589116","article-title":"On the Limited Memory BFGS Method for Large Scale Optimization","volume":"45","author":"Liu","year":"1989","journal-title":"Math. Program."},{"key":"ref_40","unstructured":"Ng, A.Y., and Jordan, M.I. (2001, January 3\u20138). On Discriminative vs. Generative classifiers: A comparison of logistic regression and naive Bayes. Proceedings of the Advances in Neural Information Processing Systems (NIPS 2001), Vancouver, BC, Canada."},{"key":"ref_41","unstructured":"Morency, L.P., Quattoni, A., Christoudias, C.M., and Wang, S. (2018, August 19). Hidden-state Conditional Random Field Library. Available online: http:\/\/pt.sourceforge.jp\/projects\/sfnet_hcrf\/."},{"key":"ref_42","unstructured":"Abed, H.E., and Margner, V. (2007, January 12\u201315). The IFN\/ENIT-database\u2014A tool to develop Arabic handwriting recognition systems. Proceedings of the 2007 9th International Symposium on Signal Processing and Its Applications, Sharjah, UAE."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Mozaffari, S., and Soltanizadeh, H. (2009, January 26\u201329). ICDAR 2009 Handwritten Farsi\/Arabic Character Recognition Competition. Proceedings of the 2009 10th International Conference on Document Analysis and Recognition, Barcelona, Spain.","DOI":"10.1109\/ICDAR.2009.283"},{"key":"ref_44","unstructured":"Chair, N.C.C., Choukri, K., Declerck, T., Dogan, M.U., Maegaard, B., Mariani, J., Moreno, A., Odijk, J., and Piperidis, S. (2012). Arabic Word Generation and Modelling for Spell Checking. Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC\u201912), European Language Resources Association (ELRA)."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Dinges, L., Al-Hamadi, A., and Elzobi, M. (2013, January 25\u201328). An Approach for Arabic Handwriting Synthesis Based on Active Shape Models. Proceedings of the 2013 12th International Conference on Document Analysis and Recognition (ICDAR), Washington, DC, USA.","DOI":"10.1109\/ICDAR.2013.255"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Bluche, T., Louradour, J., and Messina, R. (2017, January 9\u201315). Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention. Proceedings of the 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan.","DOI":"10.1109\/ICDAR.2017.174"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Moysset, B., Bluche, T., Knibbe, M., Benzeghiba, M.F., Messina, R., Louradour, J., and Kermorvant, C. (2014, January 1\u20134). The A2iA Multi-lingual Text Recognition System at the Second Maurdor Evaluation. Proceedings of the 2014 14th International Conference on Frontiers in Handwriting Recognition, Heraklion, Greece.","DOI":"10.1109\/ICFHR.2014.57"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/9\/2786\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:20:52Z","timestamp":1760196052000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/9\/2786"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,24]]},"references-count":47,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2018,9]]}},"alternative-id":["s18092786"],"URL":"https:\/\/doi.org\/10.3390\/s18092786","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2018,8,24]]}}}