Staff View: A connected component-based deep learning model for multi-type struck-out component classification

A connected component-based deep learning model for multi-type struck-out component classification

Due to the presence of struck-out handwritten words in document images, the performance of different methods degrades for several important applications, such as handwriting recognition, writer, gender, fraudulent document identification, document age estimation, writer age estimation, normal/abnorm...

Full description

Saved in:

Bibliographic Details
Main Authors:	Shivakumara, Palaiahnakote, Jain, Tanmay, Surana, Nitish, Pal, Umapada, Lu, Tong, Blumenstein, Michael, Chanda, Sukalpa
Format:	Conference or Workshop Item
Published:	2021
Subjects:	QA75 Electronic computers. Computer science T Technology (General)
Online Access:	http://eprints.um.edu.my/35417/
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.um.eprints.35417
record_format	eprints
spelling	my.um.eprints.354172023-10-17T07:20:18Z http://eprints.um.edu.my/35417/ A connected component-based deep learning model for multi-type struck-out component classification Shivakumara, Palaiahnakote Jain, Tanmay Surana, Nitish Pal, Umapada Lu, Tong Blumenstein, Michael Chanda, Sukalpa QA75 Electronic computers. Computer science T Technology (General) Due to the presence of struck-out handwritten words in document images, the performance of different methods degrades for several important applications, such as handwriting recognition, writer, gender, fraudulent document identification, document age estimation, writer age estimation, normal/abnormal behavior of person analysis, and descriptive answer evaluation. This work proposes a new method which combines connected component analysis for text component detection and deep learning for classification of struck-out and non-struck-out words. For text component detection, the proposed method finds the stroke width to detect edges of texts in images, and then performs smoothing operations to remove noise. Furthermore, morphological operations are performed on smoothed images to label connected components as text by fixing bounding boxes. Inspired by the great success of deep learning models, we explore DenseNet for classifying struck-out and non-struck-out handwritten components by considering text components as input. Experimental results on our dataset demonstrate the proposed method outperforms the existing methods in terms of classification rate. 2021 Conference or Workshop Item PeerReviewed Shivakumara, Palaiahnakote and Jain, Tanmay and Surana, Nitish and Pal, Umapada and Lu, Tong and Blumenstein, Michael and Chanda, Sukalpa (2021) A connected component-based deep learning model for multi-type struck-out component classification. In: International Workshops co-located with the 16th International Conference on Document Analysis and Recognition, ICDAR 2021, 5 - 10 September 2021, Lausanne.
institution	Universiti Malaya
building	UM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Malaya
content_source	UM Research Repository
url_provider	http://eprints.um.edu.my/
topic	QA75 Electronic computers. Computer science T Technology (General)
spellingShingle	QA75 Electronic computers. Computer science T Technology (General) Shivakumara, Palaiahnakote Jain, Tanmay Surana, Nitish Pal, Umapada Lu, Tong Blumenstein, Michael Chanda, Sukalpa A connected component-based deep learning model for multi-type struck-out component classification
description	Due to the presence of struck-out handwritten words in document images, the performance of different methods degrades for several important applications, such as handwriting recognition, writer, gender, fraudulent document identification, document age estimation, writer age estimation, normal/abnormal behavior of person analysis, and descriptive answer evaluation. This work proposes a new method which combines connected component analysis for text component detection and deep learning for classification of struck-out and non-struck-out words. For text component detection, the proposed method finds the stroke width to detect edges of texts in images, and then performs smoothing operations to remove noise. Furthermore, morphological operations are performed on smoothed images to label connected components as text by fixing bounding boxes. Inspired by the great success of deep learning models, we explore DenseNet for classifying struck-out and non-struck-out handwritten components by considering text components as input. Experimental results on our dataset demonstrate the proposed method outperforms the existing methods in terms of classification rate.
format	Conference or Workshop Item
author	Shivakumara, Palaiahnakote Jain, Tanmay Surana, Nitish Pal, Umapada Lu, Tong Blumenstein, Michael Chanda, Sukalpa
author_facet	Shivakumara, Palaiahnakote Jain, Tanmay Surana, Nitish Pal, Umapada Lu, Tong Blumenstein, Michael Chanda, Sukalpa
author_sort	Shivakumara, Palaiahnakote
title	A connected component-based deep learning model for multi-type struck-out component classification
title_short	A connected component-based deep learning model for multi-type struck-out component classification
title_full	A connected component-based deep learning model for multi-type struck-out component classification
title_fullStr	A connected component-based deep learning model for multi-type struck-out component classification
title_full_unstemmed	A connected component-based deep learning model for multi-type struck-out component classification
title_sort	connected component-based deep learning model for multi-type struck-out component classification
publishDate	2021
url	http://eprints.um.edu.my/35417/
_version_	1781704465889361920
score	13.211869

A connected component-based deep learning model for multi-type struck-out component classification

Similar Items