TSER: A Two-Stage Character Segmentation Network With Two-Stream Attention and Edge Refinement

Segmenting characters in an image is a classic yet challenging task in computer vision. Correctly determining boundaries of adhesive characters with various scales and shapes is essential for character segmentation, especially for separating handwritten characters. Nevertheless, there is seldom work...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jinyingming Zhang, Jin Liu, Xiongwei Xu, Peizhu Gong, Mingyang Duan
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2020
Materias:	Character segmentation deep learning two-stream attention mechanism cascaded edge refinement network Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/0227f8b0e0ff4db482889869c8a64264
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0227f8b0e0ff4db482889869c8a64264
record_format	dspace
spelling	oai:doaj.org-article:0227f8b0e0ff4db482889869c8a642642021-11-19T00:05:58ZTSER: A Two-Stage Character Segmentation Network With Two-Stream Attention and Edge Refinement2169-353610.1109/ACCESS.2020.3036545https://doaj.org/article/0227f8b0e0ff4db482889869c8a642642020-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9250436/https://doaj.org/toc/2169-3536Segmenting characters in an image is a classic yet challenging task in computer vision. Correctly determining boundaries of adhesive characters with various scales and shapes is essential for character segmentation, especially for separating handwritten characters. Nevertheless, there is seldom work in the literature which can achieve satisfactory performance. In this article, by leveraging the ability of deep neural networks, we proposed a two-stage character segmentation network with two-stream attention and edge refinement (TSER) to tackle this problem. TSER firstly locates every character by object detection, then extracts their corresponding contours. In the process, a novel two-stream attention mechanism (TSAM) is proposed to make the network focus more on the discrepancy of character boundaries. Furthermore, a novel generating method is used to dynamically generate anchors on different feature levels to improve model’s sensitivity on the shapes and scales of characters. Eventually a cascaded edge refinement network is used to obtain contour of each character. To prove the efficiency and generalization ability of our model, we compared TSER with traditional algorithms and other deep learning models on two commonly used datasets in different segmentation tasks. The comparative result indicated that TSER reached state-of-the-art performance.Jinyingming ZhangJin LiuXiongwei XuPeizhu GongMingyang DuanIEEEarticleCharacter segmentationdeep learningtwo-stream attention mechanismcascaded edge refinement networkElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 8, Pp 205216-205230 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Character segmentation deep learning two-stream attention mechanism cascaded edge refinement network Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Character segmentation deep learning two-stream attention mechanism cascaded edge refinement network Electrical engineering. Electronics. Nuclear engineering TK1-9971 Jinyingming Zhang Jin Liu Xiongwei Xu Peizhu Gong Mingyang Duan TSER: A Two-Stage Character Segmentation Network With Two-Stream Attention and Edge Refinement
description	Segmenting characters in an image is a classic yet challenging task in computer vision. Correctly determining boundaries of adhesive characters with various scales and shapes is essential for character segmentation, especially for separating handwritten characters. Nevertheless, there is seldom work in the literature which can achieve satisfactory performance. In this article, by leveraging the ability of deep neural networks, we proposed a two-stage character segmentation network with two-stream attention and edge refinement (TSER) to tackle this problem. TSER firstly locates every character by object detection, then extracts their corresponding contours. In the process, a novel two-stream attention mechanism (TSAM) is proposed to make the network focus more on the discrepancy of character boundaries. Furthermore, a novel generating method is used to dynamically generate anchors on different feature levels to improve model’s sensitivity on the shapes and scales of characters. Eventually a cascaded edge refinement network is used to obtain contour of each character. To prove the efficiency and generalization ability of our model, we compared TSER with traditional algorithms and other deep learning models on two commonly used datasets in different segmentation tasks. The comparative result indicated that TSER reached state-of-the-art performance.
format	article
author	Jinyingming Zhang Jin Liu Xiongwei Xu Peizhu Gong Mingyang Duan
author_facet	Jinyingming Zhang Jin Liu Xiongwei Xu Peizhu Gong Mingyang Duan
author_sort	Jinyingming Zhang
title	TSER: A Two-Stage Character Segmentation Network With Two-Stream Attention and Edge Refinement
title_short	TSER: A Two-Stage Character Segmentation Network With Two-Stream Attention and Edge Refinement
title_full	TSER: A Two-Stage Character Segmentation Network With Two-Stream Attention and Edge Refinement
title_fullStr	TSER: A Two-Stage Character Segmentation Network With Two-Stream Attention and Edge Refinement
title_full_unstemmed	TSER: A Two-Stage Character Segmentation Network With Two-Stream Attention and Edge Refinement
title_sort	tser: a two-stage character segmentation network with two-stream attention and edge refinement
publisher	IEEE
publishDate	2020
url	https://doaj.org/article/0227f8b0e0ff4db482889869c8a64264
work_keys_str_mv	AT jinyingmingzhang tseratwostagecharactersegmentationnetworkwithtwostreamattentionandedgerefinement AT jinliu tseratwostagecharactersegmentationnetworkwithtwostreamattentionandedgerefinement AT xiongweixu tseratwostagecharactersegmentationnetworkwithtwostreamattentionandedgerefinement AT peizhugong tseratwostagecharactersegmentationnetworkwithtwostreamattentionandedgerefinement AT mingyangduan tseratwostagecharactersegmentationnetworkwithtwostreamattentionandedgerefinement
_version_	1718420647979253760

TSER: A Two-Stage Character Segmentation Network With Two-Stream Attention and Edge Refinement

Ejemplares similares