4.6 Article

Self-Adaptive Hybridized Lion Optimization Algorithm With Transfer Learning for Ancient Tamil Character Recognition in Stone Inscriptions

期刊

IEEE ACCESS
卷 11, 期 -, 页码 39621-39634

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2023.3268545

关键词

Character recognition; Optimization; Feature extraction; Transfer learning; Convolutional neural networks; Optical character recognition; Classification algorithms; Lion optimization algorithm; preprocessing; stone inscription; transfer learning; Tamil character recognition

向作者/读者索取更多资源

Tamil character recognition is a challenging task in pattern recognition due to the complexity and similarity of characters compared to other languages. Stone inscriptions provide valuable insights into the history, culture, and administration of Tamil Nadu, but their preservation and understanding are hindered by erosion and incompleteness. The recognition of Tamil characters in stone inscriptions faces difficulties mainly due to the presence of characters with holes, loops, and curves.
Tamil character recognition serves as a vital research problem in pattern recognition since there are many serious technical difficulties due to similarity and complexity of characters when compared with other languages. Stone inscriptions reveal details of luxury, lifestyle, economic status, cultural practices, administrative tasks followed by various rulers and dynasties of Tamil Nadu. Since ancient stone inscriptions are in existence for a longer period, there are possibilities of natural erosion and no early protection measures are available. The ancient stone inscriptions are always not complete which creates many difficulties in reading and understanding them and their aesthetic appreciation. There is a difficulty in recognizing Tamil characters mainly because of the characters with a number of holes, loops and curves. The number of letters in Tamil language is higher when compared to other languages. Even though there are various approaches provided by the researchers, challenges and issues still prevail in recognition of tamil text in stone inscriptions. In the existing systems, detection algorithms fail to produce desired accuracy and hence stone inscription recognition using transfer learning, a promising method is proposed here. Lion Optimization Algorithm (LOA) is applied to optimize brightness and contrast and then stone inscription images are pre-processed for noise removal and then each character is separated by identifying contours. Characters are recognized using Transfer Learning (TL), a Deep Convolution Neural Network-based multi classification approach. The proposed hybrid model Self-Adaptive Lion Optimization Algorithm with Transfer Learning (SLOA-TL) when implemented in images of stone inscriptions achieves better accuracy and speed than other existing methods. It serves as an efficient design for recognition of tamil characters in stone inscriptions and preserving tamil traditional knowledge.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据