Segmentation‐based recognition system for handwritten Bangla and Devanagari words using conventional classification and transfer learning

Pramanik, Rahul; Bag, Soumen

doi:10.1049/iet-ipr.2019.0208

Cited by 25 publications

(4 citation statements)

References 34 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study adopted the CTPN or EAST character segmentation network as the main structure and proposed ResNet for feature extraction. Pramanik and Bag [9] proposed a system to detect and correct skewness in handwritten Bangla and Devanagari words. This study used a transfer learning architecture based on CNNs.…”

Section: Related Workmentioning

confidence: 99%

LONTAR_DETC: Dense and High Variance Balinese Character Detection Method in Lontar Manuscripts

2022

View full text Add to dashboard Cite

This paper proposed LONTAR_DETC, a method to detect handwritten Balinese characters in Lontar manuscripts. LONTAR_DETC is a deep learning architecture based on YOLO. The detection of Balinese characters in Lontar manuscripts is challenging due to the characteristics of Balinese characters in Lontar manuscripts. Balinese characters in Lontar manuscripts are dense, overlapping, have high variance, contain noise, and classes of these characters are imbalanced. The proposed method consists of three steps, namely data generation, Lontar manuscript annotation, and Balinese character detection. The first step is data generation, in which synthetic images of original Lontar manuscript images are generated with enhanced image quality. The second step is data annotation to build a new Lontar manuscript dataset. As a result, we also propose the Handwritten Balinese Character of Lontar manuscript (HBCL_DETC) dataset, a novel Balinese character in Lontar manuscripts dataset. HBCL_DETC contains 600 images that consists of more than 100,000 Balinese characters annotated by experts. Finally, the third step is training the YOLOv4 detection model using the HBCL_DETC dataset. We created this dataset specifically for the task of detecting Balinese characters in Lontar manuscripts. To evaluate the reliability of the dataset, we experimented with three scenarios. In the first scenario, the detection model was trained using original images of Lontar manuscripts, in the second scenario the detection model was trained with the addition of augmented grayscale images, and in the third scenario the detection model was trained using HBCL_DETC. Based on the experimental results, LONTAR_DETC can detect Balinese characters with high detection rate with mAP of 99.55%.

show abstract

Section: Related Workmentioning

confidence: 99%

LONTAR_DETC: Dense and High Variance Balinese Character Detection Method in Lontar Manuscripts

2022

View full text Add to dashboard Cite

show abstract

“…Pramanik R., Bag S. [20], proposed a method for recognising handwritten Bengali and Devanagari words that detect and correct skew present in words and then estimated the headline, segmenting the words into a meaningful pseudo character. This is the only research work that recognizes Bengali word from images as far as our knowledge.…”

Section: Related Workmentioning

confidence: 99%

“…Hence, this paper proposed an end-to-end approach that recognises handwritten Bengali words from handwritten word images. Further, experiments conducted in similar research work [20] use fewer words (at most 2000 words) in the evaluation phase. In contrast, we use 16975 words from BanglaWritting dataset to run the experiment.…”

Section: Related Workmentioning

confidence: 99%

End-to-End Optical Character Recognition for Bengali Handwritten Words

Safir¹,

Ohi²,

F.³

et al. 2021

Preprint

View full text Add to dashboard Cite

Optical character recognition (OCR) is a process of converting analogue documents into digital using document images. Currently, many commercial and non-commercial OCR systems exist for both handwritten and printed copies for different languages. Despite this, very few works are available in case of recognising Bengali words. Among them, most of the works focused on OCR of printed Bengali characters. This paper introduces an end-to-end OCR system 1 for Bengali language. The proposed architecture implements an end to end strategy that recognises handwritten Bengali words from handwritten word images. We experiment with popular convolutional neural network (CNN) architectures, including DenseNet, Xception, NASNet, and MobileNet to build the OCR architecture. Further, we experiment with two different recurrent neural networks (RNN) methods, LSTM and GRU. We evaluate the proposed architecture using BanglaWritting dataset, which is a peerreviewed Bengali handwritten image dataset. The proposed method achieves 0.091 character error rate and 0.273 word error rate performed using DenseNet121 model with GRU recurrent layer.

show abstract

“…Then, after the column with zero VP value, the first succeeding column is picked as the final segmentation point. If there isn't a vertical barrier between the letter and the connected component, CCA is used [14][15][16][17][18][19].…”

Section: Segmentationmentioning

confidence: 99%

Offline Recognition of Malayalam and Kannada Handwritten Documents Using Deep Learning

Asokan¹,

Unnithan²

2021

ijcci

View full text Add to dashboard Cite

For a variety of reasons, handwritten text can be digitalized. It is used in a variety of government entities, including banks, post offices, and archaeological departments. Handwriting recognition, on the other hand, is a difficult task as everyone has a different writing style. There are essentially two methods for handwritten recognition: a holistic and an analytic approach. The previous methods of handwriting recognition are time- consuming. However, as deep neural networks have progressed, the approach has become more straightforward than previous methods. Furthermore, the bulk of existing solutions are limited to a single language. To recognise multilanguage handwritten manuscripts offline, this work employs an analytic approach. It describes how to convert Malayalam and Kannada handwritten manuscripts into editable text. Lines are separated from the input document first. After that, word segmentation is performed. Finally, each word is broken down into individual characters. An artificial neural network is utilised for feature extraction and classification. After that, the result is converted to a word document.

show abstract

Segmentation‐based recognition system for handwritten Bangla and Devanagari words using conventional classification and transfer learning

Cited by 25 publications

References 34 publications

LONTAR_DETC: Dense and High Variance Balinese Character Detection Method in Lontar Manuscripts

LONTAR_DETC: Dense and High Variance Balinese Character Detection Method in Lontar Manuscripts

End-to-End Optical Character Recognition for Bengali Handwritten Words

Offline Recognition of Malayalam and Kannada Handwritten Documents Using Deep Learning

Contact Info

Product

Resources

About