FAN-MCCD: Fast and Accurate Network for Multi-Scale Chinese Character Detection

Inaccurate localization due to scale-variation during character detection causes a widespread issue overconfidence in results of the document analysis community, for the most part in historical and handwritten documents. In this work, we explored the performance of a state-of-the-art network with a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Manar Alnaasan, Sungho Kim
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	simple pipeline multi-scale Chinese character detection handwritten in old documents multiscale feature network Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/8676484a284b49e2abffb4c892ca66d6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8676484a284b49e2abffb4c892ca66d6
record_format	dspace
spelling	oai:doaj.org-article:8676484a284b49e2abffb4c892ca66d62021-11-11T19:14:39ZFAN-MCCD: Fast and Accurate Network for Multi-Scale Chinese Character Detection10.3390/s212172891424-8220https://doaj.org/article/8676484a284b49e2abffb4c892ca66d62021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7289https://doaj.org/toc/1424-8220Inaccurate localization due to scale-variation during character detection causes a widespread issue overconfidence in results of the document analysis community, for the most part in historical and handwritten documents. In this work, we explored the performance of a state-of-the-art network with a simple pipeline that fast and accurately predicts handwritten Chinese characters in old documents. In order to adapt to locations of characters with multi-scale more precisely, excluding pre-processing and in-between steps, we utilized a network with multi-scale feature maps. Then, across each feature map, pre-selected boxes of unalike scales and aspect ratios were employed. The last step was to prune the bounding boxes, sending them to non-maximum suppression to yield the final results. Focusing on a well-designed neural network architecture and loss function that presents well-classified examples, we found our experiments on Caoshu, Character, and Src-images datasets demonstrated that detection performance was enhanced for the detection rate (DT), the false positive per character (FPPC), and the F-score in the order of 98.84%, 0.71, and 97.64%, respectively. In comparison with SSD (single-shot detector), the detection performance of a detection rate (DT), the false positive per character (FPPC), and the F-score were 61.12%, 6.12, and 60.33%, respectively.Manar AlnaasanSungho KimMDPI AGarticlesimple pipelinemulti-scale Chinese character detectionhandwritten in old documentsmultiscale feature networkChemical technologyTP1-1185ENSensors, Vol 21, Iss 7289, p 7289 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	simple pipeline multi-scale Chinese character detection handwritten in old documents multiscale feature network Chemical technology TP1-1185
spellingShingle	simple pipeline multi-scale Chinese character detection handwritten in old documents multiscale feature network Chemical technology TP1-1185 Manar Alnaasan Sungho Kim FAN-MCCD: Fast and Accurate Network for Multi-Scale Chinese Character Detection
description	Inaccurate localization due to scale-variation during character detection causes a widespread issue overconfidence in results of the document analysis community, for the most part in historical and handwritten documents. In this work, we explored the performance of a state-of-the-art network with a simple pipeline that fast and accurately predicts handwritten Chinese characters in old documents. In order to adapt to locations of characters with multi-scale more precisely, excluding pre-processing and in-between steps, we utilized a network with multi-scale feature maps. Then, across each feature map, pre-selected boxes of unalike scales and aspect ratios were employed. The last step was to prune the bounding boxes, sending them to non-maximum suppression to yield the final results. Focusing on a well-designed neural network architecture and loss function that presents well-classified examples, we found our experiments on Caoshu, Character, and Src-images datasets demonstrated that detection performance was enhanced for the detection rate (DT), the false positive per character (FPPC), and the F-score in the order of 98.84%, 0.71, and 97.64%, respectively. In comparison with SSD (single-shot detector), the detection performance of a detection rate (DT), the false positive per character (FPPC), and the F-score were 61.12%, 6.12, and 60.33%, respectively.
format	article
author	Manar Alnaasan Sungho Kim
author_facet	Manar Alnaasan Sungho Kim
author_sort	Manar Alnaasan
title	FAN-MCCD: Fast and Accurate Network for Multi-Scale Chinese Character Detection
title_short	FAN-MCCD: Fast and Accurate Network for Multi-Scale Chinese Character Detection
title_full	FAN-MCCD: Fast and Accurate Network for Multi-Scale Chinese Character Detection
title_fullStr	FAN-MCCD: Fast and Accurate Network for Multi-Scale Chinese Character Detection
title_full_unstemmed	FAN-MCCD: Fast and Accurate Network for Multi-Scale Chinese Character Detection
title_sort	fan-mccd: fast and accurate network for multi-scale chinese character detection
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8676484a284b49e2abffb4c892ca66d6
work_keys_str_mv	AT manaralnaasan fanmccdfastandaccuratenetworkformultiscalechinesecharacterdetection AT sunghokim fanmccdfastandaccuratenetworkformultiscalechinesecharacterdetection
_version_	1718431595517444096

FAN-MCCD: Fast and Accurate Network for Multi-Scale Chinese Character Detection

Ejemplares similares