中国科学院深圳先进技术研究院机构知识库(SIAT OpenIR): A shallow convolutional neural network for blind image sharpness assessment.
SIAT OpenIR  > 医工所
A shallow convolutional neural network for blind image sharpness assessment.
Yu, Shaode; Wu, Shibin; Wang, Lei; Jiang, Fan; Xie, Yaoqin; Li, Leida
2017
Source PublicationPLOS ONE
Subtype期刊论文
AbstractBlind image quality assessment can be modeled as feature extraction followed by score prediction. It necessitates considerable expertise and efforts to handcraft features for optimal representation of perceptual image quality. This paper addresses blind image sharpness assessment by using a shallowconvolutional neural network (CNN). The network takes single feature layer to unearth intrinsic features for image sharpness representation and utilizes multilayer perceptron (MLP) to rate image quality. Different from traditional methods, CNN integrates feature extraction and score prediction into an optimization procedure and retrieves features automatically from raw images. Moreover, its prediction performance can be enhanced by replacing MLP with general regression neural network (GRNN) and support vector regression (SVR). Experiments on Gaussian blur images from LIVE-II, CSIQ, TID2008 and TID2013 demonstrate that CNN features with SVR achieves the best overall performance, indicating high correlation with human subjective judgment.
URL查看原文
Indexed BySCI
Language英语
Department微创中心
Document Type期刊论文
Identifierhttp://ir.siat.ac.cn/handle/172644/11986
Collection医工所
AffiliationPLOS ONE
Recommended Citation
GB/T 7714
Yu, Shaode,Wu, Shibin,Wang, Lei,et al. A shallow convolutional neural network for blind image sharpness assessment.[J]. PLOS ONE,2017.
APA Yu, Shaode,Wu, Shibin,Wang, Lei,Jiang, Fan,Xie, Yaoqin,&Li, Leida.(2017).A shallow convolutional neural network for blind image sharpness assessment..PLOS ONE.
MLA Yu, Shaode,et al."A shallow convolutional neural network for blind image sharpness assessment.".PLOS ONE (2017).
Files in This Item: Download All
File Name/Size DocType Version Access License
医工-微创中心2017031.pdf(7188KB) 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yu, Shaode]'s Articles
[Wu, Shibin]'s Articles
[Wang, Lei]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yu, Shaode]'s Articles
[Wu, Shibin]'s Articles
[Wang, Lei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yu, Shaode]'s Articles
[Wu, Shibin]'s Articles
[Wang, Lei]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 医工-微创中心2017031.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.