The main objective of this proposed effort is to advance the system that empowers recognition of Tamil characters from palm leaf and inscription through captured images and stock them for forthcoming use. Some training mechanism has done with several methodologies, but distinguishing Tamil characters stances challengeable mission. Tamil language is considered too complex compared to any other language because of the presences of curved, slope, twist, pits and it will vary writing style of individual to individual. More research needs adapting ancient Tamil characters to modern Tamil characters to extend the aim of creating computerized system for providing improved understanding of human knowledge. This proposed work is applicable for segmenting Tamil characters and store it in an organized system folder for further processing of the image. Gray-Level Co-occurrence Matrix (GLCM) feature extraction is used to quantify the statistical features of segmented characters. At this juncture segmented Tamil Characters are compared with Palm leaf manuscript, Stone Inscription, Handwritten characters and document characters using GLCM feature and the results are promising.

Gaussian, Bilateral, GLCM, PSNR, SSIM, MSE, Homogeneity, Angular Second Moment (ASM).

[1] Dr. Antony P J and Savitha C K, “A framework for recognition of handwritten south Dravidian Tulu script”, Conference on Advances in Signal Processing(CASP), IEEE, pp. 7 - 12, 2011.
[2] Mrs. G. Bhuvaneswari and Dr. V. Subbiah Bharathi, “An Efficient Positional algorithm for recognition of Ancient Stone Inscription Characters”, International Conference on Advanced Computing(ICoAC), IEEE, pp. 1 - 5, 2015.
[3] G. Janani, V. Vishalini and Dr. P. Mohan Kumar, “Recognition and Analysis of Tamil Inscriptions and Mapping using Image Processing Techniques”, International Conference on Science Technology Engineering and Management(ICONSTEM), IEEE, pp. 181 - 184, 2016.
[4] N Jayanthi and S Indu, “Inscription Image Retrieval using Bag of Visual words”, ICMAEM, pp. 1 - 7, 2017.
[5] Er. Kanchan Sharma, Er. Priyanka, Er. Aditi Kalsh and Er. Kulbeer Saini, “GLCM and its feature”, International Jorunal of Advanced Research in Electronics and Communication Engineering(IJARECE), Vol. 4, Issue. 8, pp. 2180-2182, 2015.
[6] Karthigaiselvi. M and T. Kathirvalavakumar, “Recognition of words in Tamil script using Neural Network”,International Journal of Computer Research and Apllication, Vol.7, Issue.3, pp. 62-70, 2017.
[7] A.S. Kavitha, P. Shivakumara, G.H. Kumar and Tong Lu, “Text Segmentation in degraded historical document images”, Egyptian Informatics Journal, Vol.17, Issue.2, pp. 189 - 197, 2016.
[8] Kavitha Subramani and Dr. S. Murugavalli, “A Novel Binarization method for degraded Tamil palm Leaf image”, International Conference on Advanced Computing(ICoAC), IEEE, pp. 176 - 181, 2016.
[9] P. Rajan and S. Sridhar, “Identification of Ancient Tamil Letters and Its characters: Automatic date fixation based on Contour-Let technique”, Association for Computing Machinery (ACM), pp. 40 – 43, 2017.
[10] Saikat Roy, Nibaran Das, Mahantapas Kundu and Mita Nasipuri, “Handwritten Isolated Bangla compound character recognition: A new benchmark using a novel deep learning approach”, Pattern Recognition Letters 90, Vol. 90, pp. 15 - 21, 2017.
[11] Shijin Kumar. P.S and Dharun V.S, “ Extraction of Texture features using GLCM and shape Features using connected regions”, International Journal of Engineering and Technology(IJET), Vol. 8, No. 6, pp. 2926-2930, 2017.
[12] M. Sornam and C. Vishnu Priya, “ Deep Convolutional Neural Network for Handwritten Tamil Character Recognition using Principal Component Analysis”, Intl. Conf. on Next Generation Computing Technologies (NGCT 17), University of Petroleum and Energy Studies, Dehradun,India, pp. 102-112, 2017.