A Novel Tri-Stage Recognition Scheme for Handwritten Malayalam Character Recognition

James, Ajay; Chandran, Saravanan

doi:10.1016/j.protcy.2016.05.137

Cited by 16 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It had correctly identified four different periods of characters with good accuracy. [16] devised a method for recognizing Malayalam characters. The feature extraction process was broken down into three steps.…”

Section: Literature Reviewmentioning

confidence: 99%

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

et al. 2023

View full text Add to dashboard Cite

Tamil character recognition is an important field of research in pattern recognition and it is a technical challenge than other languages due to similarity and complexity of characters. Stone inscriptions reveal the details of lavishness, lifestyle, economic conditions, culture, and also of the managerial regulations followed by various rulers and dynasties particular to those regions. However, due to the long history of ancient stone inscription, natural erosion and lack of early protection measures, there are lot of noise in the existing ancient stone inscriptions, which create adverse effects on reading these stone inscriptions and their aesthetic appreciation. The research challenge in recognizing Tamil characters is 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 in this paper. 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.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

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

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In the first stage the geometrical features like corner, ending, bifurcation and loop were considered and similar shaped characters were grouped into a class and in the second stage, feature extraction techniques for recognizing each character within that class was performed. In the third stage, rules regarding the formation of Malayalam word were considered for checking the probability of occurrence of the character in that position based on moment variant features, and the system achieved better recognition accuracy [26]. Nair et al proposed a method for Malayalam handwritten character recognition using CNN.…”

Section: Handwriting Recognition Studies In Malayalam Languagementioning

confidence: 99%

Review of offline handwritten text recognition in south Indian languages

Anju¹,

Chacko²,

Basheer³

2021

Malaya J. Mat.

View full text Add to dashboard Cite

Offline Handwritten character recognition is a popular and challenging area of research under pattern recognition and image processing. In this article, offline handwriting recognition methods performed in south Indian languages including Telugu, Tamil, Kannada and Malayalam are presented. A description about south Indian languages and an overview of general handwriting recognition systems are also presented briefly. Convolutional Neural Networks (CNNs) and classifier combination methods have provided better performance among proposals provided by the researchers.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Vinayakumar and Paul [29] devised a complete OCR system for recognizing printed Bengali characters which combines a template and feature matching approach [30] and it converts the image into binary formats of character strokes. This method [30] uses histogram to get two prominent peaks which corresponds to white or black regions in a clear document in which skew angle is identified from skew shaped characters. In another recognition system by Mitra et al [7] partitioning of characters in an image is done into three zones where vertical and horizontal projection profiles are applied to get segments of document image into lines of text and words and characters in deeper learning.…”

Section: Related Workmentioning

confidence: 99%

Self-Learning Based Cognitive Reading and Character Recognition in Image Processing Techniques

Kasthuri

Sivaprasatham

2020

SN COMPUT. SCI.

View full text Add to dashboard Cite

There are many techniques involved in Handwritten character recognition and many of the methods uses common process like pre-processing, segmentation, stroke identification and character interpretation. But the technique applied for these steps differ from different implementation. Building the training data is a tedious task but it is more important as the success of entire recognition system lies on the amount of training the neural network and building the knowledge base. Hence this is an important task and it is costly due to amount of time and resource used for training the dataset. This article explains some of the methods in Cognitive reading in image processing for character recognition and introduces a self-learning based training system which provides improved method in less time/resource consuming in automatically training the knowledge base.

show abstract

A Novel Tri-Stage Recognition Scheme for Handwritten Malayalam Character Recognition

Cited by 16 publications

References 17 publications

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

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

Review of offline handwritten text recognition in south Indian languages

Self-Learning Based Cognitive Reading and Character Recognition in Image Processing Techniques

Contact Info

Product

Resources

About