Devnagari handwritten character recognition (DHCR) for ancient documents: A review

Shah, Kunal; Badgujar, Dipak Dattatray

doi:10.1109/cict.2013.6558176

Cited by 11 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These issues can be rectified by using some image enhancement techniques. [6] 2. Preprocessing data :-Preprocessing data :-noise removal , binarization , slant angle correction, resize To enhance and to make it suitable preprocessing performs series of operation [7].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Comparative Analysis of Ml Classifiers for Recognition of Handwritten Devanagari Script

2022

IRJMETS

View full text Add to dashboard Cite

Devanagari has been widely adopted across India and Nepal to write Sanskrit , Marathi , Hindi , Hindi dialects , Konkani , boro and various Nepalese languages. Millions of people all in India use this script for writing documents in Hindi and Marathi. Many of the Indian mythology is written in this script. Therefore, it has received a tons of popularity over the decades. In this paper, we have taken a dataset of handwritten Devanagari characters which consist of 61200 handwritten photographs of the characters. Along with the dataset we have also proposed the deep learning algorithms for recognition of those characters named as "multi-layer perceptron classifier", "Random Forest classifier" and " K-Nearest Neighbor classifier ". The sole purpose of this paper is to compare all the three classifiers on the basis of their accuracy for recognition of the images and to come up with the best one.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Some issues while capturing the image using digital camera are blurring , shadows and text-skewing. These issues can be rectified by using some image enhancement techniques [6]. 2.…”

mentioning

confidence: 99%

Comparative Analysis of Ml Classifiers for Recognition of Handwritten Devanagari Script

2022

IRJMETS

View full text Add to dashboard Cite

show abstract

“…For any handwritten document where text orientation varies heavily for different users by using cognition reading strategy in wrong orientation should be recognized properly by automatically correcting the orientation [6]. Based on such a technique, higher accuracy ratio of about 95% is achieved [7] in experimental evaluation.…”

Section: Literature Reviewmentioning

confidence: 99%

Cognitive Reading and Character Recognition in Image Processing Techniques

Kasthuri

Sivaprasatham

2020

SN COMPUT. SCI.

View full text Add to dashboard Cite

The trend of researches in cognitive reading has become so popular in programming area in the field of computer science from late 1990s when scientists and researchers show more interests in computational approaches are complex in nature to derive from a known algorithm of solution. For instance, in the research areas of biology, medicine and human management sciences there are various problems where we need cognitive reading to deliver a complex and in-exact solution when there is no polynomial time to arrive at an exact solution. This article explains some of the methods in cognitive reading in image processing for character recognition and briefly discusses the steps involved in the process of character recognition in image processing.

show abstract

“…Offline handwritten word recognition constitutes a predominant segment of the Optical Character Recognition (OCR) domain [1]. This task is extensively utilized across various applications, including the scanning of medical reports, recognition of words in doctor prescriptions [2], conversion of ancient manuscripts [3] into machine-editable formats, automated assessment of answer sheets, digit identification on cheques, and more. The surge in handwritten content during the COVID pandemic has underscored the necessity of processing this data and transitioning it into a format amenable to machine editing.…”

Section: Introductionmentioning

confidence: 99%

“…The digitization of the Marathi script-the language predominantly used in the Indian state of Maharashtrapresents a formidable challenge that demands increased scholarly focus to render it into an editable format. Historically, several algorithms have been developed to analyze and comprehend the recognition tasks of individual characters and digits within Marathi manuscripts [3][4][5]. The Devanagari script, which encompasses the Marathi language, consists of 10 numerals, 11 vowels, and 37 consonants.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Recognition of Offline Marathi Handwriting via a Self-Additive Attention Mechanism

Chikmurge,

Raghunathan

2023

View full text Add to dashboard Cite

Background: Offline Marathi handwriting recognition presents a significant challenge due to the script's complexity and the variability of individual writing styles. Methods: In the present work, an advanced encoder-decoder framework is introduced, wherein a novel selfadditive-attention mechanism is integrated. This model capitalizes on a Convolutional Neural Network paired with a Joint Scale Feature Extractor (CNN-JSE) to discern low-level image features within the IIIT-HW-Dev dataset. Such features are subsequently fed into an encoder model that employs a dual-phase fusion process: initially leveraging a Bidirectional Long Short-Term Memory (BiLSTM) network, followed by the self-additive-attention mechanism to maintain dependencies over extensive sequences. Results: The fusion output, comprising BiLSTM and self-additive attention data, is conveyed to a Connectionist Temporal Classifier (CTC) decoder. This decoder adeptly identifies character sequences within Marathi words. The introduction of self-additive attention alongside BiLSTM is instrumental in preserving dependencies that are both long-range and multi-stage. Performance Evaluation: The efficacy of the proposed system was rigorously evaluated on the multi-author IIIT-HW-Dev dataset. Performance metrics, specifically Character Error Rate (CER) and Word Error Rate (WER), were employed for benchmarking against various established models. Conclusion: The proposed methodology demonstrates a significant enhancement in the recognition of handwritten Marathi text, thus facilitating the conversion of handwritten documents into machine-editable text. The utilization of selfadditive attention within the BiLSTM framework underscores its potential in capturing complex dependencies, setting a new precedent in automated handwriting recognition technologies. Significance: This study not only paves the way for increased accuracy in handwritten text recognition but also contributes a novel approach to the encoding of feature sequences, which may be applicable to a broad range of pattern recognition applications.

show abstract

Devnagari handwritten character recognition (DHCR) for ancient documents: A review

Cited by 11 publications

References 10 publications

Comparative Analysis of Ml Classifiers for Recognition of Handwritten Devanagari Script

Comparative Analysis of Ml Classifiers for Recognition of Handwritten Devanagari Script

Cognitive Reading and Character Recognition in Image Processing Techniques

Enhanced Recognition of Offline Marathi Handwriting via a Self-Additive Attention Mechanism

Contact Info

Product

Resources

About