Overview: Handwriting recognition (HR) involves converting handwritten text into machinereadable text. Tamil handwritten document recognition remains a challenging process in various real-world applications owing to the differences in the sizes, styles and orientation angles of Tamil alphabets. Prior studies concentrated only on character-level segmentation, and each character was subsequently classified. The recently developed machine learning (ML) and deep learning (DL) approaches can be utilized for Tamil handwritten character recognition (HCR). Objective: This paper attempts to present an end-to-end DL-based Tamil handwritten document recognition (ETEDL-THDR) model. Methods: Segmentation is used, first at the word level and then at the line level. ETEDL-THDR text recognition can be accomplished using two modules: line segmentation and line recognition. Initially, the ETEDL-THDR model targets improving input image quality using the median filtering (MF) technique. To create meaningful regions, more line and character segmentation activities are performed. A deep convolutional neural network (DCNN) based MobileNet approach is also applied to derive feature vectors. Finally, the water strider optimization (WSO) algorithm with a bidirectional gated recurrent unit (BiGRU) model is used to identify the Tamil characters. Results: Extensive experimental analyses of the ETEDL-THDR model have been carried out, and the results show that the ETEDL-THDR model performs better than more recent methodologies, with a maximum accuracy of 98.48%, a precision of 98.38%, a sensitivity of 97.98%, specificity of 98.27% and F-measure of 98.35%. Conclusion: The comparison results show that the proposed model can recognize Tamil handwritten documents in real time.
Handwritten recognition (HR) remains a challenging process in various real-world applications. Tamil handwritten text recognition involves the recognition of text in scanned images. Recognition of handwritten Tamil characters is a tedious process because of the differences in sizes, style and orientation angle. Prior studies concentrated on character-level segmentation and each character was subsequently classified. Segmentation is then used, first at the word level and subsequently at the line level. The recently developed machine learning (ML) and deep learning (DL) approaches can be utilized for Tamil HCR. With this motivation, this paper presents an end-to-end deep learning-enabled Tamil handwritten document recognition (ETEDL-THDR) model. The ETEDL-THDR paragraph text recognition can be accomplished by the use of two modules such as line segmentation and line recognition. Initially, the ETEDL-THDR model enables the improvement of the quality of the input images by the use of the median filtering (MF) technique. To create meaningful regions, further line and character segmentation activities are performed. Additionally, a deep convolutional neural network-based MobileNet approach was applied to derive feature vectors. At last, the water strider optimization (WSO) algorithm with a bidirectional gated recurrent unit (BiGRU) model is applied to recognize Tamil characters. An extensive experimental analysis of the ETEDL-THDR model is carried out and the results showed that the ETEDL-THDR model performed better than more recent methodologies with maximum accuracy of 98.48%, precision of 98.38%, a sensitivity of 97.98%, specificity of 98.27%, and F-measure of 98.35%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.