GMANet: Gradient Mask Attention Network for Finding Clearest Human Fecal Microscopic Image in Autofocus Process

The intelligent recognition of formed elements in microscopic images is a research hotspot. Whether the microscopic image is clear or blurred is the key factor affecting the recognition accuracy. Microscopic images of human feces contain numerous items, such as undigested food, epithelium, bacteria...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiangzhou Wang, Lin Liu, Xiaohui Du, Jing Zhang, Guangming Ni, Juanxiu Liu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	blind image quality assessment deep convolutional neural network human fecal microscopic image gradient mask attention Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/3d3d8aa63f3b4a5d9b7d998a57841612
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3d3d8aa63f3b4a5d9b7d998a57841612
record_format	dspace
spelling	oai:doaj.org-article:3d3d8aa63f3b4a5d9b7d998a578416122021-11-11T15:19:25ZGMANet: Gradient Mask Attention Network for Finding Clearest Human Fecal Microscopic Image in Autofocus Process10.3390/app1121102932076-3417https://doaj.org/article/3d3d8aa63f3b4a5d9b7d998a578416122021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10293https://doaj.org/toc/2076-3417The intelligent recognition of formed elements in microscopic images is a research hotspot. Whether the microscopic image is clear or blurred is the key factor affecting the recognition accuracy. Microscopic images of human feces contain numerous items, such as undigested food, epithelium, bacteria and other formed elements, leading to a complex image composition. Consequently, traditional image quality assessment (IQA) methods cannot accurately assess the quality of fecal microscopic images or even identify the clearest image in the autofocus process. In response to this difficulty, we propose a blind IQA method based on a deep convolutional neural network (CNN), namely GMANet. The gradient information of the microscopic image is introduced into a low-level convolutional layer of the CNN as a mask attention mechanism to force high-level features to pay more attention to sharp regions. Experimental results show that the proposed network has good consistency with human visual properties and can accurately identify the clearest microscopic image in the autofocus process. Our proposed model, trained on fecal microscopic images, can be directly applied to the autofocus process of leucorrhea and blood samples without additional transfer learning. Our study is valuable for the autofocus task of microscopic images with complex compositions.Xiangzhou WangLin LiuXiaohui DuJing ZhangGuangming NiJuanxiu LiuMDPI AGarticleblind image quality assessmentdeep convolutional neural networkhuman fecal microscopic imagegradient mask attentionTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10293, p 10293 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	blind image quality assessment deep convolutional neural network human fecal microscopic image gradient mask attention Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	blind image quality assessment deep convolutional neural network human fecal microscopic image gradient mask attention Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Xiangzhou Wang Lin Liu Xiaohui Du Jing Zhang Guangming Ni Juanxiu Liu GMANet: Gradient Mask Attention Network for Finding Clearest Human Fecal Microscopic Image in Autofocus Process
description	The intelligent recognition of formed elements in microscopic images is a research hotspot. Whether the microscopic image is clear or blurred is the key factor affecting the recognition accuracy. Microscopic images of human feces contain numerous items, such as undigested food, epithelium, bacteria and other formed elements, leading to a complex image composition. Consequently, traditional image quality assessment (IQA) methods cannot accurately assess the quality of fecal microscopic images or even identify the clearest image in the autofocus process. In response to this difficulty, we propose a blind IQA method based on a deep convolutional neural network (CNN), namely GMANet. The gradient information of the microscopic image is introduced into a low-level convolutional layer of the CNN as a mask attention mechanism to force high-level features to pay more attention to sharp regions. Experimental results show that the proposed network has good consistency with human visual properties and can accurately identify the clearest microscopic image in the autofocus process. Our proposed model, trained on fecal microscopic images, can be directly applied to the autofocus process of leucorrhea and blood samples without additional transfer learning. Our study is valuable for the autofocus task of microscopic images with complex compositions.
format	article
author	Xiangzhou Wang Lin Liu Xiaohui Du Jing Zhang Guangming Ni Juanxiu Liu
author_facet	Xiangzhou Wang Lin Liu Xiaohui Du Jing Zhang Guangming Ni Juanxiu Liu
author_sort	Xiangzhou Wang
title	GMANet: Gradient Mask Attention Network for Finding Clearest Human Fecal Microscopic Image in Autofocus Process
title_short	GMANet: Gradient Mask Attention Network for Finding Clearest Human Fecal Microscopic Image in Autofocus Process
title_full	GMANet: Gradient Mask Attention Network for Finding Clearest Human Fecal Microscopic Image in Autofocus Process
title_fullStr	GMANet: Gradient Mask Attention Network for Finding Clearest Human Fecal Microscopic Image in Autofocus Process
title_full_unstemmed	GMANet: Gradient Mask Attention Network for Finding Clearest Human Fecal Microscopic Image in Autofocus Process
title_sort	gmanet: gradient mask attention network for finding clearest human fecal microscopic image in autofocus process
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/3d3d8aa63f3b4a5d9b7d998a57841612
work_keys_str_mv	AT xiangzhouwang gmanetgradientmaskattentionnetworkforfindingclearesthumanfecalmicroscopicimageinautofocusprocess AT linliu gmanetgradientmaskattentionnetworkforfindingclearesthumanfecalmicroscopicimageinautofocusprocess AT xiaohuidu gmanetgradientmaskattentionnetworkforfindingclearesthumanfecalmicroscopicimageinautofocusprocess AT jingzhang gmanetgradientmaskattentionnetworkforfindingclearesthumanfecalmicroscopicimageinautofocusprocess AT guangmingni gmanetgradientmaskattentionnetworkforfindingclearesthumanfecalmicroscopicimageinautofocusprocess AT juanxiuliu gmanetgradientmaskattentionnetworkforfindingclearesthumanfecalmicroscopicimageinautofocusprocess
_version_	1718435360815448064

GMANet: Gradient Mask Attention Network for Finding Clearest Human Fecal Microscopic Image in Autofocus Process

Ejemplares similares