OFFLINE YORÙBÁ HANDWRITTEN WORD RECOGNITION USING GEOMETRIC FEATURE EXTRACTION AND SUPPORT VECTOR MACHINE CLASSIFIER
DOI:
https://doi.org/10.24191/mjoc.v5i2.8947Keywords:
Gradient, Handwritten, Offline, Pre-processing, Support Vector Machine, Word, Yorùbá, ZoningAbstract
Yorùbá language is one of the three main languages that is been spoken in Nigeria. It is a tonal language that carries an accent on the vowel alphabets. There are twenty-five (25) alphabets in Yorùbá language with one of the alphabets a digraph (GB). Due to the difficulty in typing handwritten Yorùbá documents, there is a need to develop a handwritten recognition system that can convert the handwritten texts to digital format. This study discusses the offline Yorùbá handwritten word recognition system (OYHWR) that recognizes Yorùbá uppercase alphabets. Handwritten characters and words were obtained from different writers using the paint application and M708 graphics tablets. The characters were used for training and the words were used for testing. Pre-processing was done on the images and the geometric features of the images were extracted using zoning and gradient-based feature extraction. Geometric features are the different line types that form a particular character such as the vertical, horizontal, and diagonal lines. The geometric features used are the number of horizontal lines, number of vertical lines, number of right diagonal lines, number of left diagonal lines, total length of all horizontal lines, total length of all vertical lines, total length of all right slanting lines, total length of all left-slanting lines and the area of the skeleton. The characters are divided into 9 zones and gradient feature extraction was used to extract the horizontal and vertical components and geometric features in each zone. The words were fed into the support vector machine classifier and the performance was evaluated based on recognition accuracy. Support vector machine is a two-class classifier, hence a multiclass SVM classifier least square support vector machine (LSSVM) was used for word recognition. The one vs one strategy and RBF kernel were used and the recognition accuracy obtained from the tested words ranges between 66.7%, 83.3%, 85.7%, 87.5%, and 100%. The low recognition rate for some of the words could be as a result of the similarity in the extracted features.
References
Abdul Rahman, A. N. C., Abdullah, I. H., Zainuddin, I. S., & Jaludin, A. (2019). The Comparisons of OCR Tools: A Conversion Case in the Malaysian Hansard Corpus Development. Malaysian Journal of Computing, 4 (2), 335-348.
Adeyanju, I., Fenwa, O., & Omidiora, E. O. (2014). Effect of non-image features on recognition of handwritten alpha-numeric characters. International Journal of Computers and Technology. 2014,13.
Ajao, J. F., Olabiyisi, S. O., Omidiora, E. O., & Okediran, O. O. (2016). Hidden Markov Model Approach for Offline Yorùbá Handwritten Word Recognition. British Journal of Mathematics & Computer Science, 18(6), 1-20.
Ajao, J. F., Olawuyi D. O., & Odejobi, O. O. (2018). Yoruba Handwritten Character Recognition using Freeman Chain Code and K-Nearest Neighbor Classifier. Jurnal Teknologi dan Sistem Komputer, 6(2), 129-134.
Arica, N., & Yarman-Vural, F. (2001). An Overview of Character Recognition Focused on Off-Line Handwriting. IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 31(2), 216 - 233.
Awni, M., Khalil, M. I., & Abbas, H. M. (2019). Deep-Learning Ensemble for Offline Arabic Handwritten Words Recognition. 2019 14th International Conference on Computer Engineering and Systems (ICCES), Cairo, Egypt. 40 - 45.
Fan, D., Gao, G., & Wu, H. (2019). Sub-Word Based Mongolian Offline Handwriting Recognition. International Conference on Document Analysis and Recognition (ICDAR), Sydney, Australia, 246 - 253.
Mhetre, S. L., & Patil, P. S. (2013). Comparative study of two methods for Handwritten Devanagari Numeral Recognition. IOSR Journal of Computer Engineering (IOSR-JCE), 15(6), 49-53.
Oladele, M. O., Adepoju, T. M., Omidiora, E. O., Sobowale, A. A., Olatoke, O. A., & Ayeleso E. C (2017). An Offline Yorùbá Handwritten Character Recognition System Using Support Vector Machine. International Conference of Science, Engineering & Environmental Technology (ICONSEET), 2(13), 95 - 103.
Pant, A. K., Panday, S. P., & Joshi, S. R. (2012). Off-line Nepali handwritten character recognition using Multilayer perceptron and Radial basis function Neural network, 3rd Asian Himalayas International Conference on Internet, Kathmandu, Nepal, November 2012.
Pradeep, J., Srinivasan, E., & Himavathi, S. (2011). Diagonal based feature extraction for handwritten character recognition system using neural network. 2011 3rd International Conference on Electronics Computer Technology, Kanyakumari, 2011, 364 - 368.
Pupale, R. (2018). Support Vector Machines (SVM) - An Overview. A post at Towards data science available at https://towardsdatascience.com/https-medium-com-pupalerushikesh-svm-f4b42800e989
Rahman, M., Mahmud, I., Uddin, P., Afjal, M., Habib, A., & Kabir, F. (2019). Handwritten Bengali Character Recognition Through Geometry-Based Feature Extraction. Journal of Theoretical and Applied Information Technology, 97(23), 3570 - 3582.
Ray, S. (2017). Understanding Support Vector Machine (SVM) algorithm from examples (along with code). A post at Analytics Vidhya available at https://www.analyticsvidhya.com/blog/2017/09/understaing-support-vector-machine-example-code/
Sepahvand, M., Abdali-Mohammadi, F., & Mardukhi, F. (2017). Evolutionary Metric-Learning Based Recognition Algorithm for Online Isolated Persian/Arabic Characters, Reconstructed Using Inertial Pen Signals. IEEE Transactions on Cybernetics, 47(9), 2872 - 2884.
Shanjana, C., & James, A. (2015). Offline Recognition of Malayalam Handwritten Text. In 8th International Conference Interdisciplinarity in Engineering, INTER-ENG 2014, 9th – 10th October 2014, Tirgu-Mures, Romania. 772-779.
Sonawane, P. K., & Shelke, S. (2018). Handwritten Devanagari Character Classification using Deep Learning. 2018 International Conference on Information, Communication, Engineering, and Technology (ICICET), Pune, 1-4.
Tawde, G. Y. & Kundargi, J. M. (2013). An Overview of Feature Extraction Techniques in OCR for Indian Scripts Focused on Offline Handwriting. International Journal of Engineering Research and Applications (IJERA), 3(1).
Vinothini, R., & Subalalitha, C. N. (2020). Offline Handwritten Character Recognition System for Tamil Language. International Journal of Advanced Science and Technology, 29(5), 4912 - 4918.
Published
Issue
Section
License
Copyright (c) 2020 Matthias Omotayo Oladele, Temilola Morufat Adepoju, Olaide Abiodun Olatoke, Oluwaseun Adewale Ojo
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
