Xianxu Hou
Direct Application of Convolutional Neural Network Features to Image Quality Assessment
Hou, Xianxu; Sun, Ke; Liu, Bozhi; Gong, Yuanhao; Garibaldi, Jonathan; Qiu, Guoping
Authors
Ke Sun
Bozhi Liu
Yuanhao Gong
Prof. JONATHAN GARIBALDI JON.GARIBALDI@NOTTINGHAM.AC.UK
Provost and Pvc Unnc
GUOPING QIU GUOPING.QIU@NOTTINGHAM.AC.UK
Professor of Visual Information Processing
Abstract
© 2018 IEEE. We take advantage of the popularity of deep con-volutional neural networks (CNNs) and have developed a very simple image quality assessment method that rivals state of the art. We show that convolutional layer outputs (deep features) of a CNN compute the local structural information of spatial regions of different sizes in the input image. The learned convolutional kernels contain a much richer set of weights thus capturing much more local structural information than hand crafted ones. As the deep features learned from large datasets already contain very rich multi-resolutional structural image information, they can be directly used to calculate visual distortion of an image and it is not necessary to introduce further complicated computational process. We will present experimental results to demonstrate that this is indeed the case, and that simple cosine distance of the deep features is as good as state the art methods for full reference image quality assessment.
Citation
Hou, X., Sun, K., Liu, B., Gong, Y., Garibaldi, J., & Qiu, G. (2018). Direct Application of Convolutional Neural Network Features to Image Quality Assessment. In 2018 IEEE Visual Communications and Image Processing (VCIP). https://doi.org/10.1109/VCIP.2018.8698726
Presentation Conference Type | Conference Paper (Published) |
---|---|
Conference Name | IEEE Visual Communications and Image Processing (VCIP 2018) |
Start Date | Dec 9, 2018 |
End Date | Dec 12, 2018 |
Acceptance Date | Aug 1, 2018 |
Online Publication Date | Apr 25, 2019 |
Publication Date | Jul 2, 2018 |
Deposit Date | Jun 17, 2019 |
Publicly Available Date | Jun 17, 2019 |
Publisher | Institute of Electrical and Electronics Engineers |
Series Title | IEEE Visual Communications and Image Processing (VCIP) |
Book Title | 2018 IEEE Visual Communications and Image Processing (VCIP) |
ISBN | 9781538644584 |
DOI | https://doi.org/10.1109/VCIP.2018.8698726 |
Keywords | CNN, Deep features, Image quality assessment |
Public URL | https://nottingham-repository.worktribe.com/output/2198017 |
Publisher URL | https://ieeexplore.ieee.org/document/8698726 |
Additional Information | © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
Contract Date | Jun 17, 2019 |
Files
Direct Application of Convolutional
(1.2 Mb)
PDF
You might also like
MysiRNA-designer: a workflow for efficient siRNA design
(2011)
Journal Article
Signalling Paediatric Side Effects using an Ensemble of Simple Study Designs
(2014)
Journal Article
From Interval-Valued Data to General Type-2 Fuzzy Sets
(2014)
Journal Article
Augmented Neural Networks for modelling consumer indebtness
(2014)
Presentation / Conference Contribution
A comparison between two types of Fuzzy TOPSIS method
(2015)
Presentation / Conference Contribution
Downloadable Citations
About Repository@Nottingham
Administrator e-mail: discovery-access-systems@nottingham.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search