Title: Ancient epigraphical monuments' convolution neural network-based skeletonised structural angular morphing character identification intelligent systems

Authors: P. Selvakumar

Addresses: Department of Computer Science, Government Arts College, Ariyalur, Tamil Nadu, 621713, India; Affiliated to: Bharathidasan University, India

Abstract: Tamil is one of the oldest languages, and it is based on several proofs from ancient Kiladhi epigraphic monuments. Tamil texts have various structural styles and projections identified from monuments like palm lead characters, vattezhuthu, and stone inscriptions. By projecting Tamil characters in various angles, the text style may vary due to structural representation, leading the actual character style to differentiate from the old style. Thus, recognition of the specific projection of the old character leads to more features on the dimension level to get the Tamil character and classification. Consider skeletonised structural angular morphing (S2AM) based on a CNN-identified Tamil character from ancient epigraphic monuments for optimum identification. Epigrammatic images will be pre-processed using Gaussian filters, and then SMS will glide the character region using CED. Use the skeletonised angular projection to discover text structural components and extract angular information. The selected features will be trained with a DFCNN to find the Tamil character. The suggested system outperforms other outdated character recognition methods in precision, sensitivity, and false detection accuracy.

Keywords: script systems identifying; Tamil character detection; edge detection skeletonisation; character identification intelligent systems; canny edge detection; CED; deep featured convolution neural network; DFCNN; sliding morphological segmentation; SMS; convolution neural network; CNN.

DOI: 10.1504/IJRIS.2026.153560

International Journal of Reasoning-based Intelligent Systems, 2026 Vol.18 No.3, pp.143 - 154

Received: 16 Jul 2024
Accepted: 03 Oct 2024
Published online: 14 May 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article