Abstract
The core aspiration of this proposed work is to classify Tamil characters inscribed in the palm leaf manuscript using an Artificial Neural Network. Tamil palm leaf manuscript characters in the form of images were processed and segmented using contour-based convex hull bounding box segmentation. The segmented characters were transformed into two forms: Binary Coded Value and the Gray-Level Co-occurrence Matrix (GLCM) feature. The features extracted from the segmented characters were trained by the proposed method of the Modified Adaptive Backpropagation Network (MABPN) algorithm with Shannon activation function. Weight initialization plays an important role in the Backpropagation Neural Network, and hence Nguyen-Widrow weight initialization was introduced to initialize the weights instead of random weight initialization in the proposed method. The models evaluated are MABPN with Shannon activation function using Nguyen-Widrow weight initialization in two forms of input: Binary Coded Value and GLCM feature extracted values. The proposed method with GLCM features as input gave a promising result over binary coded transform.
- P. E. Ajmire. 2017. Handwritten Devanagari vowel recognition using artificial neural network. International Journal of Advanced Research in Computer Science 8, 7 (2017), 1059--1062.Google Scholar
Cross Ref
- Amit Choudhary, Rahul Rishi, and Savita Ahlawat. 2013. Off-line handwritten character recognition using features extracted from binarization techniques. AARSI Procedia 4 (2013), 306--312.Google Scholar
Cross Ref
- P. J. Antony and C. K. Savitha. 2016. A framework for recognition of handwritten South Dravidian Tulu script.In Proceedings of the 2016 IEEE Conference on Advances in Signal Processing (CASP’16). 7--12.Google Scholar
- V. C. Bharathi and N. Kalaiselvi Geetha. 2013. Segregated handwritten character recognition using GLCM features. International Journal of Computer Applications 84 (2013), 1--7.Google Scholar
Cross Ref
- Carlo Cattani. 2008. Shannon wavelets theory. Mathematical Problems in Engineering 2008 (2008), Article 164808.Google Scholar
- Dino Neinhold, Kilian Schwab, Rolf Dornberger, and Thomas Hanne. 2015. Effects of weight initialization in a feedforward neural network for classification using a modified genetic algorithm. In Proceedings of the 2015 IEEE 3rd International Symposium on Computationaland Business Intelligence. 6--12.Google Scholar
Digital Library
- M. Hossin and M. N. Sulaiman. 2015. A review on evaluation metrics for data classification evaluation. International Journal of Data Mining 8 Knowledge Management Process 5, 2 (2015), 1--11.Google Scholar
- S. Jeyaseeli Subavathi and T. Kathirvalavakumar. 2011. Adaptive modified backpropagation algorithm based on differential errors. International Journal of Computer Science, Engineering and Applications 1 (2011), 21--34.Google Scholar
- E. Kanchan Sharma, E. Priyanka, E. Aditi Kalsh, and E. Kulbeer Saini. 2015. GLCM and its features. International Journal of Advanced Research in Electronics and Communication Engineering 4, 8 (2015), 2180--2182.Google Scholar
- M. Karthigaiselvi and T. Kathirvalavakumar. 2017. Structural run based feature vector to classify printed Tamil characters using neural network. International Journal of Engineering Research and Application 7, 7 (2017), 44--63.Google Scholar
Cross Ref
- K. G. N. D. Karunarathne, K. V. Liyanage, D. A. S. Ruwanmini, G. K. A. Dias, and S. T. Nandasara. 2017. Recognizing ancient Sinhala inscription characters using neural network technologies. International Journal of Scientific Engineering and Applied Science 3, 1 (2017), 37--48.Google Scholar
- Kavitha Subramani and S. Murugavalli. 2016. A novel binarization method for degraded Tamil palm leaf images. In Proceedings of the 2016 IEEE 8th International Conference on Advanced Computing (ICoAC’16). 176--181.Google Scholar
- B. Kiruba, A. Nivethitha, and M. Vimaladevi. 2017. Segmentation of handwritten Tamil character from palm script using histogram approach. International Journal of Informative and Futuristic Research 4, 5 (2017), 6418--6424.Google Scholar
- A. Lenin Fred, S. N. Kumar, H. Ajay Kumar, Ashy V. Daniel, and W. Abisha. 2018. Evaluation of local thresholding techniques in palm-leaf manuscript images. International Journal of Computer Sciences and Engineering 6, 4 (2018), 124--131.Google Scholar
Cross Ref
- Narahari Sastry Panyam, T. R. Vijaya Lakshmi, Ramakrishnan Krishnan, and N. V. Koteswara Rao. 2016. A modeling of palm leaf character recognition system using transform based techniques. Pattern Recognition Letters 84 (2016), 29--34.Google Scholar
Digital Library
- Neeraj Sharma, Amit K. Ray, Shiru Sharma, K. K. Shukla, Satyajit Pradhan, and Lalit M. Aggarwa. 2008. Segmentation and classification of medical images using texture-primitive features: Application of BAM-type artificial neural network. Journal of Medical Physics 33, 3 (2008), 119--126.Google Scholar
Cross Ref
- Nibaran Das, Jagan Mohan Reddy, Ram Sarkar, Subhadip Basu, Mahantapas Kundu, Mita Nasipuri, and Dipak Kumar Basu. 2012. A statistical-topological feature combination for recognition of handwritten numerals. Applied Soft Computing 12 (2012), 2486--2495.Google Scholar
Digital Library
- Sk Md Obaidullah, Chayan Halder, Nibarab Das, and Kaushik Roy. 2015. Numeral script identification from handwritten document images. Procedia Computer Science 54, 12 (2015), 585--594.Google Scholar
Cross Ref
- Prathima Guruprasad and Jharna Majumdar. 2017. Optical clustering technique for handwritten Nandinagari character recognition. International Journal of Computer Application Technology and Research 6, 5 (2017), 2319--8656.Google Scholar
Cross Ref
- P. Rajan and S. Sridhar. 2017. Identification of ancient Tamil letters and its characters: automatic date fixation based on Contour-let technique. In Proceedings of the International Conference on Graphics and Signal Processing (ICGSP’17). 40--43, https://doi.org/10.1145/3121360.3121384Google Scholar
- K. Rajan, V. Ramalingam, M. Ganesan, S. Palanivel, and B. Palaniappan. 2009. Automatic classification of Tamil documents using vector space model and artificial neural network. Expert Systems with Applications 36 (2009), 10914--10918.Google Scholar
Digital Library
- Robert M. Haralick, K. Shanmugam and Its’Hak Dinstein. 1973. Textural features for image classification. IEEE Transactions on System, Man and Cybernetics 3 (1973), 610--621.Google Scholar
Cross Ref
- Sachin S. Bhat and H. V. Balachandra Achar. 2016. Character recognition and period prediction of ancient Kannada epigraphical scripts. International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control Engineering 3, 1 (2016), 114--118.Google Scholar
- R. S. Sabeenian, M. E. Paramasivam, P. M. Dinesh, R. Adarsh, and Gokul Ravi Kumar. 2017. Classification of handwritten Tamil characters in palm leaf manuscripts using SVM based smart zoning strategies. In Proceedings of the 2nd International Conference on Biomedical Signal and Image Processing (ICBIP’17). ACM, New York, NY, 18--21.Google Scholar
Digital Library
- Saikat Roy, Nibaran Das, Mahantapas Kundu, and Mita Nasipuri. 2017. Handwritten isolated Bangla compound character recognition: A new benchmark using novel deep learning approach. Pattern Recognition Letters 90 (2017), 15--21.Google Scholar
Cross Ref
- Shahnaz Abu Akker Bapputty Haji, Ajay James, and Saravanan Chandran. 2016. A novel segmentation and skew correction approach for handwritten Malayalam documents. Procedia Technology 24 (2016), 1341--1348.Google Scholar
Cross Ref
- K. Sonu Varghese, Ajay James, and Saravanan Chandran. 2016. A novel tri-stage recognition scheme for handwritten Malayalam character recognition. Procedia Technology 24 (2016), 1333--1340.Google Scholar
Cross Ref
- M. Sornam and Poornima Devi. M. 2018. Tamil palm leaf manuscript character segmentation using GLCM feature extraction. International Journal of Computer Science and Engineering 6, 4 (2018), 167--173.Google Scholar
- M. Sornam, Muthu Subash Kavitha, and Poornima Devi. M. 2016. An efficient Morlet function based adaptive method for faster backpropagation for handwritten character recognition. In Proceedings of the 2016 IEEE International Conference on Advances in Computer Applications (ICACA’16). 135--139.Google Scholar
Cross Ref
- M. Sornam and C. Vishnu Priya. 2018. Deep convolutional neural network for handwritten Tamil character recognition using principal component analysis. In Smart and Innovative Trends in Next Generation Computing Technologies. Springer, 778--787.Google Scholar
- Tien-Chien Chang and Shu-Yuan Chen. 1999. Character segmentation using convex hull techniques. International Journal of Pattern Recognition and Artificial Intelligence 13, 6 (1999), 833--858.Google Scholar
Cross Ref
- E. K. Vellingiriraj, M. Balamurugan, and P. Balasubramanie. 2016. Information extraction and text mining of ancient Vattezhuthu characters in historical documents using image zoning. In Proceedings of the 2016 IEEE International Conference on Asian Language Processing (IALP’16). 37--40.Google Scholar
- E. K. Vellingiriraj and P. Balasubramanie. 2014. Recognition of ancient Tamil handwritten characters in historical documents by Boolean matrix and BFS graph. International Journal of Computer Science and Technology 5 (2014), 65--68.Google Scholar
- T. R. Vijaya Lakshmi. 2017. Reduction of features to identify characters from degraded historical manuscripts. Alexandria Engineering Journal 57, 4 (2017), 2393--2399.Google Scholar
Cross Ref
- Yaping Zang, Shan Liang, Shuai Nie, Wenju Liu, and Shouye Peng. 2018. Robust offline handwritten character recognition through exploring writer-independent features under the guidance of printed data. Pattern Recognition Letters 106 (2018), 20--26.Google Scholar
Cross Ref
- Yi-Chao Wu, Fei Yin, and Cheng-Lin Liu. 2017. Improving handwritten Chinese text recognition using neural network language models and convolutional neural network shape models. Pattern Recognition 65 (2017), 251--264.Google Scholar
Digital Library
Index Terms
Classification of Ancient Handwritten Tamil Characters on Palm Leaf Inscription Using Modified Adaptive Backpropagation Neural Network with GLCM Features
Recommendations
Classification of Handwritten Tamil Characters in Palm Leaf Manuscripts Using SVM Based Smart Zoning Strategies
ICBIP '17: Proceedings of the 2nd International Conference on Biomedical Signal and Image ProcessingPalm leaf manuscripts has been one of the ancient methods for writingbut with timethe quality of palm leaf manuscripts degrades and the content needs to be scribed in new set of leaves. In this paper, we have presented an alternate solution to save the ...
Neural Network Based Offline Tamil Handwritten Character Recognition System
ICCIMA '07: Proceedings of the International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007) - Volume 02In this paper we propose an approach to recognize handwritten Tamil characters using a multilayer perceptron with one hidden layer. The feature extracted from the handwritten character is Fourier Descriptors. Also an analysis was carried out to ...
Neural Network Based Offline Tamil Handwritten Character Recognition System
ICCIMA '07: Proceedings of the International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007) - Volume 02In this paper we propose an approach to recognize handwritten Tamil characters using a multilayer perceptron with one hidden layer. The feature extracted from the handwritten character is Fourier Descriptors. Also an analysis was carried out to ...






Comments