Articles
Template Matching Method for Recognition of Stone Inscripted Kannada Characters of Different Time Frames Based on Correlation Analysis
Downloads
Keywords
Template Matching
Kannada Character Recognition
Stone Inscriptions
Correlation Analysis
Article Usage Statistics
Live Metrics
Abstract Views
174
File Views
85
PDF
0
HTML
0
Other
85
Total
259
Article Usage Chart
Abstract
File Views
PDF
HTML
Other
Total
Abstract
Stone inscriptions serve as critical historical artifacts, preserving linguistic, cultural, and administrative records of past civilizations. The recognition of stone-inscripted Kannada characters across different centuries presents unique challenges due to the combined effects of temporal variations in script style, surface erosion, uneven engraving, and environmental degradation. Traditional optical character recognition (OCR) methods, designed for printed or handwritten text, often fail to handle these complexities effectively. This research proposes a template matching method based on correlation analysis to accurately identify Kannada characters in stone inscriptions, accommodating variations across different historical periods.
The proposed methodology integrates advanced preprocessing techniques, including noise reduction, contrast enhancement, and segmentation, to improve character visibility and reduce the impact of surface irregularities. Multi-temporal templates are constructed to represent stylistic evolution of Kannada script, allowing the system to match input characters with reference templates using normalized cross-correlation. The framework includes post-processing refinement, employing structural constraints and contextual analysis to reduce false positives and ensure accurate character recognition.
Experimental evaluation on a dataset of over 1,200 stone-inscribed characters demonstrates that the proposed approach achieves an overall recognition accuracy of 91.3%, outperforming conventional SIFT-based and neural network-based methods in terms of interpretability and computational efficiency for small datasets. The system exhibits robustness against partial erosion, stroke deformation, and minor lighting variations, making it suitable for both research and preservation applications.
This study contributes to the intersection of computational linguistics, cultural heritage digitization, and pattern recognition by providing a replicable, efficient, and historically aware framework for recognizing temporally variant Kannada inscriptions. The findings underscore the potential of correlation-based template matching as a practical and interpretable alternative to resource-intensive machine learning approaches, offering significant implications for historical manuscript archiving, educational platforms, and automated epigraphy analysis.
Downloads
Download data is not yet available.
References
1. Ahmad Abdulkader Matthew R Casey. Low Cost Correction of OCR Errors Using Learning in a Multi-Engine Environment. IEEE10.1109/ICDAR.2009.242. IJECE ISSN: 2088-8708 Template Matching Method for Recognition of Stone Inscripted Kannada Characters of ... (Rajithkumar B K) 729
2. B Dai, D Zhang, H Liu, S Sun, and K Li. Evaluation of face recognition techniques. Proc. Of SPIE. 2009; 7489: 74890M-1-74890M-7.
3. Chaudhuri BB and Pal U. “A complete printed bangla OCR system”. Pattern Recognition. 1998; 31(5): 531-549.
4. Dipti Deodhare, et al. Preprocessing and image enhancement algorithms for a Form-based Intelligent Character Recognition System. IJCSA. 2005; 2(2): 131-144.
5. Dr HS Mohana, et al. Era Identification and Recognition of Stone In-scripted Kannada Characters Using Artificial Neural Networks. 2nd National Conference on Innovation in Computing and Communication Technology. 2014.
6. Dr HS Mohana, et al. Extraction of Stone In-scripted Kannada Characters Using Sift Algorithm Based Image Mosaic. International Journal of Electronics & Communication Technology, IJECT. 2014; 5(2).
7. G Rajput, Rajeswari Horakeri, Sidramappa Chandrakant. Printed and Handwritten Mixed Kannada Numerals Recognition Using SVM. Department of Computer Science, Gulbarga University, Gulbarga, Karnataka-India.
8. HS Mohana. Machine Vision Based Non-Magnetic Object Detection and Removal on Moving Conveyors in Steel Industry through Differential Techniques. International Journal of Computer Vision and Image Processing (IJCVIP). 2012; 2(3), accessed (March 14, 2014).
9. Historians study pushes earliest record of Kannada writing back by a century. Retrieved 2013-07-19.
10. Izakian H, Monadjemi SA, Ladani BT and Zamanifar K. “Multi-Font Farsi/Arabic Isolated Character Recognition Using Chain Codes”. World Academy of Science, Engineering and Technology. 2008: 43.
11. K Mikolajczyk and C Schmid. A performance evaluation of local descriptors. IEEE Trans. Pattern Analysis and Machine Intelligence. 2005; 27(10): 1651-1630.
12. Maalinee Ramu. Printed Number Recognition using Matlab. UNIVERSITY TEKNOLOGI, MALAYSIA.
13. Mohammed Ali Qatran. Template matching method for recognition Musnad characters based on correlation analysis. Department of Computer Science, Amran University, Yemen.
14. Mori S, Suen CY and Yanamoto K. “Historical review of OCR research and development”. Proc. of the IEEE. 1992; 80: 1029-1058.
15. Rafel C Gonzalez, Richard E. woods. Digital Image processing (2nd edition).
16. Sarfraz M, Jameel M and Ghazi S. “Saudi Arabian License Plate Recognition System”. Proc. Inte. Conf. on Geom. Modeling and Graph. 2003: 1985-7.
17. Tappert C, Suen C and Wakahara T. “The stateof the art in online handwriting recognition”. IEEE Trans. On Pattern Anal. And Machine Intel. 1990; 12(8): 787 - 808.
18. Tappert C, Suen C and Wakahara T. “The stateof the art in online handwriting recognition”. IEEE Trans. on Pattern Anal. And Machine Intel. Vol. 12, Issue 8, 787 - 808, 1990.
19. Serge Belongie, Member, IEEE, Jitendra Malik. Shape Matching and Object Recognition Using Shape Contexts. IEEE transactions on patternanalysis and machine intelligence. 2002; 24(24).