Master Thesis Defense: Utku Ülkü
  • FENS
  • Master Thesis Defense: Utku Ülkü

You are here




Utku Ülkü
Computer Science and Engineering, M.Sc. Thesis, 2013 

Thesis Jury
Assoc. Prof. Berrin Yanıkoğlu (Thesis Supervisor), Assoc. Prof. Yücel Saygın, Assoc. Prof.  Cem Güneri, Assoc. Prof. Selim Balcısoy, Prof. Dr. Muhammet Köksal 

Date &Time: August 13th, 2013 – 11:00

Place: FENS L063

Keywords: handwriting, recognition, online, mathematical, expression


This thesis presents MathLet v3 which is the third version of a system developed to recognize handwritten mathematical expressions. Previous versions were developed by Hakan Büyükbayrak and Mehmet Çelik.

MathLet v3 implements two steps to recognize handwritten mathematical expression: symbol recognition and parsing. In the symbol recognition step, two classifiers are combined. One of these classifiers uses online features while the other one uses offline features. Both classifiers return probability distributions over classes.

In the parsing step, probability distributions are used to increase time performance of MathLet v3. Moreover, parallel programming is used in parsing phase. Special handling approach for mistaken symbols is also implemented in the parsing step.

MathLet v3 has four editions and two of them can be accessed through the Web. Users write mathematical expressions or upload existing InkML files which contain mathematical expression and get recognition results for them through the Web by using these editions.

MathLet has been participating in a competition named CROHME since 2011. The evaluation results of MathLet in CROHME showed that the accuracy of MathLet has increased from 0.55\% to 8.35\% starting from 2011 although recognition task become more difficult in each year. In addition to accuracy improvements, experiments made to measure time performance of MathLet v3 show that MathLet v3 has become faster.