Handwritten Tamil Character Recognition Using Zernike Moments and Legendre Polynomial

Wahi, Amitabh; Sundaramurthy, S.; Poovizhi, P

doi:10.1007/978-81-322-2135-7_63

Cited by 10 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zernike moments captures the orthogonal features by dividing the image into a series of radial and angular polynomial moments. Each Zernike moment corresponds to a specific combination of Legendre polynomials which represent the features which are invariant to scale, transformation and rotation [38]. Using these techniques, 32 moments based on features and 69 diagonal features from each zone were extracted for Tamil characters [39].…”

Section: Feature Extractionmentioning

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: Feature Extractionmentioning

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

“…Overall, the proposed approach achieved recognition accuracy of up to 96.11%, a significant improvement compared to other state-of-theart methods, and 99.52% accuracy was for the AlexU-W dataset. Wahi et al (2015) utilized ResNet-50 in their work as it is a key feature of Tamil character recognition because it allows for the efficient training of hundreds or thousands of layers. ResNet-50 uses an "identity short connection" layer to overcome the problem of the gradient becoming very small with more layers, which allows for fewer and no deep layers in the system.…”

Section: Fig 3: Cnn Architecturementioning

confidence: 99%

A Comprehensive Overview of Handwritten Recognition Techniques: A Survey

Ali¹,

Abdulrazzaq²

2023

Journal of Computer Science

View full text Add to dashboard Cite

Deep learning and deep neural networks, particularly ConvolutionalNeural Networks (CNNs), are rapidly growing areas of machine learning and are currently the primary tools used for image analysis and classification applications. Handwriting recognition involves using computer algorithms and software to interpret and recognize handwritten text and drawings and has various applications such as automated handwriting analysis, document digitization, and handwriting-based user interfaces. Many deep learning models have been applied in the field of handwriting recognition and various datasets have been used to evaluate new computer vision techniques. This article provides an overview of the current state-of-the-art approaches and contributions to handwriting recognition using different datasets. Furthermore, the paper explains the most commonly used algorithms for recognizing handwritten characters, words, and numbers. Compares them based on their accuracy. This study covered different aspects and methods of machine learning and Deep Learning (DL) for handwritten recognition that showed different achievements for each.

show abstract

“…The output obtained could not be digitally segmented due to the lack of availability of any language parser for ancient Tamil scripts. To develop efficient systems for recognizing the Indian languages, especially for Tamil, a south Indian language that is widely used in Tamilnadu, Srilanka, and Pudhucherry, Singapore [10]. For dataset collection, they included the images of letters that are written and scanned.…”

Section: Related Workmentioning

confidence: 99%

Analysis of Various Deep learning Algorithms for Tamil Character Recognition

Kumar¹,

J²,

D³

2021

Proceedings of the First International Conference on Combinatorial and Optimization, ICCAP 2021, December 7-8 2021, Chennai, In

View full text Add to dashboard Cite

Process of converting Handwritten Tamil letters into editable form for extracting the information present in documents, Invoices that in handwritten letters that are difficult to find out the word present in the document because of bad handwriting and poor quality of the picture, Social media comments for analyzing and extracting the sentiment behind the text. Nowadays people started to deliver their thoughts through their own language Native Tamil. People find it easy to post thighs in Tamil which also leads to false information, violated messages, and cyberbullying. To address this, the notion of deep learning algorithms is implemented to classify the letters in digital form and also to suggest that the combination of letters obtained from deep learning results in better performance and good accuracy as well. The method involves the identification of optical characters to obtain feedback for the model and the creation of a model using neural networks which include CNN, Yolo and ResNet. Existing works involves using a simple OCR system but it results in a low-level recognition rate it finds difficult blurred images, shaken images, slightly tilted image's, poor quality images to recognize the text and give it back as an editable form to overcome this above situation selecting these models for testing with the Tamil character's to choose upon the best fit model to proceed for the future work of increasing the dataset and to recognize all the combination of words given in the input source of Tamil letters. The dataset used here is from HP-Labs India, which provides a large dataset of around 60,000 samples of isolated Tamil letters collected from both male and female candidates with different age groups. Tamil text classification is generally used to classify particular letters from handwritten letters in the digital form of images.

show abstract

Handwritten Tamil Character Recognition Using Zernike Moments and Legendre Polynomial

Cited by 10 publications

References 14 publications

Ancient Character Recognition: A Comprehensive Review

Ancient Character Recognition: A Comprehensive Review

A Comprehensive Overview of Handwritten Recognition Techniques: A Survey

Analysis of Various Deep learning Algorithms for Tamil Character Recognition

Contact Info

Product

Resources

About