Open Access Open Access  Restricted Access Subscription or Fee Access

An Enhanced Algorithm with Combined Feature Extraction and Neural Network Approach for Recognition of Handwritten Mathematical Expressions

Sagar Shinde, Dr. R. B. Waghulade

Abstract


Identification of math symbols and expressions is an inspired task due to its 2D layout, complex semantics and spatial structure. Extracting math expressions from document is more tangled. Actually many approaches have been proposed for better recognition of math expressions but does not resolved ambiguities in some cases of complex handwritten mathematical expressions. In the proposed recognition system, fusion of machine learning and combined feature extraction (boundary box, counting elements, height to width ration, and area of elements) is evaluated by feed forward back propagation neural network. The experimentation and analysis has been carried out for various kinds of handwritten mathematical expressions. The difficulties in recognition of complex handwritten mathematical expressions have been solved by training the neural network with scaled conjugate gradient in proposed methodology. The system verifies its strength and potential. The proposed method enhanced the speed of recognition with expecting results and confusion matrix shows the accuracy of 98.6%.

Keywords


Boundary Box, Complex Semantics, Confusion Matrix, Counting Elements, Offline Identification, Machine Learning, Math Expressions, Math Symbols, Scaled Conjugate Gradient, Spatial Structure.

Full Text:

PDF

References


Ahmad-Montaser Awal, Harold Mouchere, Christian Viard-Gaudin, “Towards Handwritten Mathematical Expressions Recognition”, IEEE 10th International Conference on Document Analysis and Recognition (ICDAR), Barcelone, Spain, ISBN: 978-0-7695-3725-2, 2009, 1046-1050.

Xuedong Tian, Yan Zhang, “Segmentation of Touching Characters in Mathematical Expressions Using Contour Feature Technique “, IEEE Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing, (SNPD- 2007), Qingdao, ISBN: 978-0-7695-2909-7, 2007,206 – 209.

Dae Hwan Kim, Jin H. Kim, “Top-Down Search with Bottom-Up Evidence for Recognizing Handwritten Mathematical Expressions ” , International Conference on Frontiers in Handwriting Recognition (ICFHR), Conference Location: Kolkatta, ISBN : 978-1-4244-8353-2, 2010, 507 – 512.

Al Hamad H.A, “Use an efficient neural network to improve the Arabic handwriting recognition”, IEEE International Conference on Signal and Image Processing Applications, Melaka, ISBN: 978-1-4799-0267-5, 2013, 269 – 274.

Ming-hu Ha, Xue-dong Tian, Na Li, “Structural analysis of printed mathematical expressions based on combined strategy”, International Conference on Machine Learning and Cybernetics, Conference Location: Dalian, China, ISBN: 1-4244-0061-9, 2006, 3354 – 3358.

Koschinski M., Winkler H.-J., Lang M, “ Segmentation and Recognition Of Symbols Within Handwritten Mathematical Expressions”, International Conference on Acoustics, Speech, and Signal Processing (ICASSP-95), Detroit, USA, Vol. 4, 1995, 2439-2442.

Nafiz Arica, “An offline –character recognition system for free style handwriting” A thesis submitted to the graduate school of natural and applied sciences of the Middle East technical university, 1998.

Francisco – Alvaro, Joan Andrue Sanchez, “Comparing several techniques for offline recognition of printed mathematical symbols”, 20th International conference on pattern recognition, IEEE computer society, Location: Istanbul, ISSN: 1051-4651, 2010, 1953-1956.

Mehmet celik, Berin Yanicoglu, “Probabilistic Mathematical Formula Recognition Using a 2D Context-Free Graph Grammar” international conference on document analysis and recognition(ICDAR), DOI 10.1109/ICDAR.2011.41, 2011, 161-166.

Anshul Gupta, Manisha Shrivastava, “Offline Handwritten character recognition”, A Thesis submitted in IIT, Guwahati, 2011.

SV Rajashekhararadhya and P vanaja Ranjan,“ Zone based hybrid feature extraction algorithm for handwritten numeral recognition of two popular Indian scripts” IEEE world congress on Nature and Biologically Inspired Computing ( NaBIC 2009), Location: Coimbatore, ISBN: 978-1-4244-5053-4, 2009, 526-530.

Laurence Likforman-Sulem, “ Recent approaches in handwriting recognition with markovian modeling and recurrent neural networks” , Proceedings of the 23rd Workshop of the Italian Neural Networks Society (SIREN), Vietri sul Mare, Salerno, Italy Smart innovation, Systems and Technologies 26, ISBN : 978-3-319-04129-2 Springer, 2014, 261-267.

Thedore Bluche, Hermann Ney and Christopher Kermorvant, “feature extraction with convolutional neural network for handwritten word recognition” IEEE - 12th International conference on Document analysis and recognition (ICDAR), Location: Washington, DC, ISSN: 1520-5363, 2013, 285-289.

Zahra Imani, Alireza ahmadyfard, Abbas Zohrevand, Mohamad Alipour, “Offline handwritten farsi cursive text recognition using hidden markov models ” IEEE- 8th Iranian conference on machine vision and image processing ( MVIP), Location : Zanjan, ISSN: 2166-6776, 2013, 75-79.

Bingyu chi and youbin chen, “Chinese handwritten legal amount recognition with hidden markov model approach” IEEE- 12th international conference Document analysis and Recognition( ICDAR), ISSN: 1520-5363, Location : Washington, DC, 2013, 778-782.

Amal Ramzi and Ammar Zahary, “Online Arabic handwritten character recognition using online – offline feature extraction and back propagation neural network” IEEE- 1st international conference on advanced technologies for signal and image processing (ATSIP), Location: Sousse, 2014, 350-355.

Ahn duc LE, Truyen Van PHAN, Masaki , “ A system for recognizing online handwritten mathematical expressions and improvement of structure analysis” IEEE- 11th international workshop on Document analysis systems(DAS) ,Location : Tours, ISBN : 978-1-4799-3243-6, 2014, 51-55.

Chen Liu, Lina Zuo, Xinfu Li, Xuedong Tian, “An improved algorithm for Identifying Mathematical formulas in the images of PDF documents” IEEE International Conference on Progress in Informatics and Computing (PIC) . Location: Nanjing, ISBN: 978-1-4673-8086-7, 2015, 252-256.


Refbacks

  • There are currently no refbacks.