Isolated Handwritten Tamil Character Recognition using Convolutional Neural Networks

Ulaganathan, Nagul; Rohith, J; S, Sri Aravind; Abhinav, A S; Vijayakumar,; Lakshmanan, L.

doi:10.1109/iciss49785.2020.9315945

Cited by 14 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model used double and triple skip layers with non-linearity and batch normalization [52]. Other than convolution layer and max pooling layer, CNN models incorporate regularization and dropouts to improve the accuracy [53]. A simple CNN developed for hand written character recognition was able to achieve a good accuracy i.e., a recognition rate above 80%.…”

Section: E Classificationmentioning

confidence: 99%

Ancient Character Recognition: A Comprehensive Review

Krithiga,

Varsini,

Gabriel Joshua

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Deep learning-based character recognition of Tamil inscriptions plays a significant role in preserving the ancient Tamil language. The complexity of the task lies in the precise classification of the age-old Tamil letters (Vattezhuthu) into modern-day Tamil letter structures. Various methodologies and pre-processing techniques have been used for denoising the ancient Tamil manuscript to retrieve the Tamil text. Researchers have used various synthesized and scanned images of stone wall inscriptions, palm leaves manuscripts, and offline handwritten characters for their analysis. Over the years, Ancient Tamil scripts have deteriorated with time due to various natural calamities. Strong denoising and feature extraction methods are required to separate the letters accurately to tackle this issue. Techniques such as CNN(OCR), ResNet, SVM, KNN, HorVer method, etc., are utilized to digitize Tamil characters. This technique has successfully converted handwritten characters into digitalized text for multiple languages, including Tamil, Arabic, English, Latin, Chinese, German, etc. Different models have been evaluated based on their segmentation and recognition rates, accuracy, detection rate, precision, and confusion matrix. This paper will concentrate on Ancient Tamil character segmentation and recognition models. Besides, we will give an overview of the different models and datasets available. Lastly, we summarise the key challenges and the future scope related to the topic.

show abstract

Section: E Classificationmentioning

confidence: 99%

Ancient Character Recognition: A Comprehensive Review

Krithiga,

Varsini,

Gabriel Joshua

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Ulaganathan et al [16] recommended a new architecture of CNN for handwritten TCR. The method of utilizing CNN for the detection of handwritten characters varies from other classical methods in feature extraction.…”

Section: Kowsalya and Periasamymentioning

confidence: 99%

End-To-End Deep Learning Based Tamil Handwritten Document Recognition and Classification Model

Vinotheni¹,

Pandian²

2022

Preprint

View full text Add to dashboard Cite

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%.

show abstract

“…The automation of document processing plays a critical role in tackling the operational challenges related to tasks like search, retrieval, and data extraction. The need for this arises due to the continuous generation of large volumes of documents daily [2], [3]. Automatic document processing faces several challenges, such as complex data structures, significant similarities within classes, differences between classes, and the risk of scanned document corruption caused by various distortions [4], [5].…”

Section: Introductionmentioning

confidence: 99%

Graph attention-driven document image classification through DualTune learning

Shilpa,

Soma

2024

IJEECS

View full text Add to dashboard Cite

Document image classification is a challenging task due to the complexity of information contained within documents, including text, images, and their spatial arrangement. Deep learning has become a pivotal tool for extracting and learning complex patterns. However, conventional methods often grapple with integrating different data modalities and minimizing redundancy, leading to a need for more advanced and efficient deep learning strategies. This study presents a new approach to document image classification, named graph attention-driven with dual tune learning (GAD-DTL). GAD-DTL employs dual-tune learning and graph attention networks. The methodology creates semantic region embedding within document images, which incorporate both textual and spatial data. A key feature of this approach is the adaptive fusion layer, which integrates different modalities and uses a graph attention layer to capture context within each region. To minimize redundancy in learned features, we implement two distinct learning techniques, relational and non-relational learning. This approach enhances document image classification by ensuring invariant representation and minimal redundancy in features.

show abstract

Isolated Handwritten Tamil Character Recognition using Convolutional Neural Networks

Cited by 14 publications

References 20 publications

Ancient Character Recognition: A Comprehensive Review

Ancient Character Recognition: A Comprehensive Review

End-To-End Deep Learning Based Tamil Handwritten Document Recognition and Classification Model

Graph attention-driven document image classification through DualTune learning

Contact Info

Product

Resources

About