Ottoman Script Recognition Using Hidden Markov Model

In this study, an OCR system for segmentation, feature extraction and recognition of Ottoman Scripts has been developed using handwritten characters. Detection of handwritten characters written by humans is a difficult process. Segmentation and feature extraction stages are based on geometrical feature analysis, followed by the chain code transformation of the main strokes of each character. The output of segmentation is well-defined segments that can be fed into any classification approach. The classes of main strokes are identified through left-right Hidden Markov Model (HMM).

Authors:

• Ayşe Onat
• Ferruh Yildiz
• Mesut Gündüz

Keywords:

• Chain Code
• HMM
• Ottoman Script Recognition
• OCR

References:

[1] Lorigo Liana M., Offline Arabic Handwriting Recognition, IEEE
Transactions On Pattern Analysis and Machine Intelligience,Vol 28, No
5, May 2006.
[2] Mcandrew Alas Dair, Digital Image Processing with Matlab, Thomson
Course Technology.
[3] At─▒c─▒ Alper, Segmentation, Feature Extraction and Recognition of
Ottoman Script, September 1994.
[4] Motawa Deya, Amin Adnan and Sabourin Robert, Segmentation of
Arabic Cursive Script.
[5] ChengXiang Zhai, A Brief Note on the Hidden Markov Models (HMMs),
March 16, 2003.
[6] Alaa M.Gouda, M.A.Rashwan, Segmentation of Connected Arabic
Characters Using Hidden Markov Models , CIMSA 2004 IEEE
lnternetional Conference on Computational Intelligence for
Measurement Systems and Applications Baston, YD, USA, 14-16 July
2004.