CRFs and HCRFs Based Recognition for Off-Line Arabic Handwriting
This paper investigates the application of the probabilistic discriminative based Conditional Random Fields (CRFs) and its extension the hidden-states CRFs (HCRFs) to the problem of off-line Arabic handwriting recognition. A CRFs- and A HCRFs- based classifiers are built on top of an explicit word segmentation module using two different set of shape description features. A simple yet effective taxonomization technique is used to reduce the number of the class labels, and 3000 letter samples from IESK-arDB database are used for the training and 300 words are used for the evaluation. Experiments compare the performance of the CRFs to the HCRFs as well as to that of a generative based HMMs. Results indicate superiority of discriminative based approaches, where HCRFs achieved the best performance followed by CRFs.
KeywordsRecognition Rate Class Label Hide State Conditional Random Field Gradient Ascent
This work is supported by the National Plan for Science, Technology and Innovation (MAARIFAH) - King Abdulaziz City for Science and Technology(KACST) - KSA. Project code: 13-INF604-10.
- 1.Sutton, C., McCallum, A.: An introduction to conditional random fields (2010)Google Scholar
- 3.Feng, S., Manmatha, R., Mccallum, A.: Exploring the use of conditional random field models and HMMs for historical handwritten document recognition. In: the Proceedings of the 2nd IEEE International Conference on Document Image Analysis for Libraries (DIAL), pp. 30–37Google Scholar
- 4.Elzobi, M., Al-Hamadi, A., Al Aghbari, Z., Dings, L.: IESK-arDB: A database for handwritten Arabic and an optimized topological segmentation approach. Int. J. Doc. Anal. Recogn. (IJDAR) 16, 1–14 (2012)Google Scholar
- 5.Likforman-Sulem, L., AlHajj Mohammad, R., Mokbel, C., Menasri, F., Bianne-Bernard, A.L., Kermorvant, C.: Features for HMM-Based Arabic handwritten word recognition systems. In: Maergner, V., El Abed, H. (eds.) Guide to OCR for Arabic Scripts, pp. 123–143. Springer, London (2002)Google Scholar
- 9.Zhu, Y., Yu, J., Jia, C.: Initializing k-means clustering using affinity propagation. In: 2009 Ninth International Conference on Hybrid Intelligent Systems, HIS 2009, vol. 1, pp. 338–343 (2009)Google Scholar
- 11.Quattoni, A., Wang, S., Morency, L., Collins, M., Darrell, T., Csail, M.: Hidden-state conditional random fields. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2007)Google Scholar
- 12.Elzobi, M., Al-Hamadi, A., Dings, L., Elmezain, M., Saeed, A.: A hidden Markov model-based approach with an adaptive threshold model for off-line Arabic handwriting recognition. In: ICDAR, pp. 945–949 (2013)Google Scholar
- 13.Morency, L.P., Quattoni, A., C.M.C., Wang, S.: Hidden-state conditional random field library (2012). http://pt.sourceforge.jp/projects/sfnethcrf/