Abstract
Simpler methods of feature extraction and better accuracy have always been primary needs of a handwriting recognition system to be a successful real-time system. The novelty of this paper lies in the introduction of two unique methods of feature extraction which are Pixel Moment of Inertia (PMI) and Delta Distance Coding (DDC). PMI absorbs angular variations in the samples and DDC performs précised local curve coding for better recognition accuracy. Multiple Hidden Markov Model (MHMM) has been used to neutralize the effect of two very frequent writing styles of numerals “4” and “7” on their recognition rates. The paper uses MNIST database, and overall recognition accuracy of 99.01% has been achieved.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Karungaru S, Terada K, Fukumi M (2013) Hand written character recognition using star-layered histogram features. In: SICE annual conference 2013, Nagoya University, Japan, p 1151
Bhattacharya U, Chaudhuri B (2009) Handwritten numeral databases of indian scripts and multistage recognition of mixed numerals. IEEE Trans Pattern Anal Mach Intell 31(3):444–457
Wang B, Zhang L, Wang X (2013) A classification algorithm in Li-K nearest neighbor. In: Fourth global congress on intelligent systems. ISBN: 978-1-4799-2886-6/13 (IEEE)
Torres LA, Méndez JC, Luis E, Gómez G (2000) Translation, rotation, and scale-invariant object recognition. IEEE Trans Syst Man Cybern Part c Appl Rev 30(1):125–130
Wen Y, Lu Y, Yan J, Zhou Z, von Deneen KM, Shi P (2011) An algorithm for license plate recognition applied to intelligent transportation system. IEEE Trans Intell Transport Syst 12(3):830–845
Zhao B, Liu Y, Xia SW (2000) Support vector machines and its application in handwritten numerical recognition. In: 15th international conference on pattern recognition, vol 2, pp 720–723
Ding K, Liu ZB, Jin LW, Zhu XH (2007) A comparative study of Gabor feature and gradient feature for handwritten Chinese character recognition. In: ICWAPR, Beijing, China, pp 1182–1186
Fujisawa H, Liu CL (2003) Directional pattern matching for character recognition. In: 7th ICDAR, Edinburgh, Scotland, pp 794–798
Liu CL, Nakashima K, Sako H, Fujisawa H (2004) Handwritten digit recognition: investigation of normalisation and feature extraction techniques. Patt Recogn 37(2):265–279
El Abed H, Margner V (2011) ICDAR—Arabic handwriting recognition competition. Int J Doc Anal Recogn 14:3–13
El-Hajj R, Likforman-Sulem L, Mokbel C (2005) Arabic hand-writing recognition using baseline dependent features and hidden markov modeling. In: Eighth international conference document analysis and recognition, pp 893–897
Mokbel C, Abi Akl H, Greige H (2002) Automatic speech recognition of Arabic digits over Telephone network. In: Research trends in science and technology, RSTS’02, Beyrouth
Natarajan P, Saleem S, Prasad R, MacRostie E, Subramanian K (2008) Multilingual off-line handwriting recognition using hidden Markov models: a script independent approach. Springer Book Chapter on Arabic and Chinese Handwriting Recognition, vol 4768, pp 235–250. ISSN: 0302-9743
Rabiner LR (1998) A tutorial on Hidden Markov Models and selected applications in speech recognition. In: Proceedings of the IEEE, vol 77, no 2, pp 257–286
Kallio S, Kela J, Korpipää P, Mäntyjärvi J (2006) User independent gesture interaction for small handheld devices. Int J Patt Recogn Artif Intell 20(4):505–524
Kim S, Park G, Yim S, Choi S, Choi S (2009) Gesture-recognizing hand-held interface with vibrotactile feedback for 3D interaction. IEEE Trans Consum Electron 55(3):1169–1177
Hsu YL, Chu CL, Tsai YJ, Wang JS (2015) An inertial pen with dynamic time warping recognizer for handwriting and gesture recognition. IEEE Sens J 15(1):154–163
Abou-Moustafa KT, Cheriet M, Suen CY (2004) On the structure of hidden Markov models. Patt Recogn Lett 25:923–931 (Elsevier)
Babu U, Venkateswarlu Y, Chintha A (2014) Handwritten digit recognition using K-nearest neighbour classifier. In: Proceedings of world congress on computing and communication technologies
Mayraz G, Hinton GE (2002) Recognizing handwritten digits using hierarchical products of experts. IEEE Trans Patt Anal Mach Intell 24:189–197
Zhao Z, Liu CL, Zhao M (2013) Handwriting representation and recognition through a sparse projection and low-rank recovery framework. Int Joint Conf Neural Netw (IJCNN), 1–8
Acknowledgements
MNIST database is a universally accepted benchmark database of English or Arabic numerals available on the link “Y. LeCun [MNIST OCR data]”. This database has been used in this proposed work. I am thankful to the authority of Guru Nanak Institutions Technical Campus, Ibrahimpatnam, T.S. India to provide us with Internet and other allied facilities to carry out research works.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Prasad, B.K. (2019). Moment of Inertia-Based Approach to Recognize Arabic Handwritten Numerals. In: Saini, H., Singh, R., Kumar, G., Rather, G., Santhi, K. (eds) Innovations in Electronics and Communication Engineering. Lecture Notes in Networks and Systems, vol 65. Springer, Singapore. https://doi.org/10.1007/978-981-13-3765-9_26
Download citation
DOI: https://doi.org/10.1007/978-981-13-3765-9_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-3764-2
Online ISBN: 978-981-13-3765-9
eBook Packages: EngineeringEngineering (R0)