BLIND HIGH DYNAMIC RANGE IMAGE QUALITY ASSESSMENT USING DEEP LEARNING

Sen Jia; Yang Zhang; Dimitris Agrafiotis; David Bull

doi:10.1109/ICIP.2017.8296384

BLIND HIGH DYNAMIC RANGE IMAGE QUALITY ASSESSMENT USING DEEP LEARNING

Sen Jia, Yang Zhang, Dimitris Agrafiotis, David Bull

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

24 Citations (Scopus)

285 Downloads (Pure)

Abstract

In this paper we propose a No-Reference Image Quality Assessment (NR-IQA) method on High Dynamic Range (HDR) images by combining deep Convolutional Neural Networks (CNNs) with saliency maps. The proposed method utilises the power of deep CNN architectures to extract quality features which can be applied cross HDR and Standard Dynamic Range (SDR) domains. To introduce human visual system to CNNs, a saliency map algorithm is used to select a subset of salient image patches to evaluate on. Our CNN-based method delivers a state-of-the-art performance in HDR NR-IQA experiment, competitive with full reference IQA methods.

Original language	English
Title of host publication	IEEE International Conference on Image Processing (ICIP)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Number of pages	5
ISBN (Electronic)	9781509021758
ISBN (Print)	9781509021765
DOIs	https://doi.org/10.1109/ICIP.2017.8296384
Publication status	Published - 22 Feb 2018

Publication series

Name	IEEE International Conference on Image Processing (ICIP)
Publisher	IEEE
ISSN (Electronic)	2381-8549

Access to Document

10.1109/ICIP.2017.8296384

Full-text PDF (accepted author manuscript)
This is the accepted author manuscript (AAM). The final published version (version of record) is available online via IEEE at https://doi.org/10.1109/ICIP.2017.8296384 . Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 468 KBLicence: Other

Handle.net

Persistent link

Cite this

@inproceedings{99cc60fffabd401584fb76c52e5a4791,

title = "BLIND HIGH DYNAMIC RANGE IMAGE QUALITY ASSESSMENT USING DEEP LEARNING",

abstract = "In this paper we propose a No-Reference Image Quality Assessment (NR-IQA) method on High Dynamic Range (HDR) images by combining deep Convolutional Neural Networks (CNNs) with saliency maps. The proposed method utilises the power of deep CNN architectures to extract quality features which can be applied cross HDR and Standard Dynamic Range (SDR) domains. To introduce human visual system to CNNs, a saliency map algorithm is used to select a subset of salient image patches to evaluate on. Our CNN-based method delivers a state-of-the-art performance in HDR NR-IQA experiment, competitive with full reference IQA methods.",

author = "Sen Jia and Yang Zhang and Dimitris Agrafiotis and David Bull",

year = "2018",

month = feb,

day = "22",

doi = "10.1109/ICIP.2017.8296384",

language = "English",

isbn = "9781509021765",

series = "IEEE International Conference on Image Processing (ICIP)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

booktitle = "IEEE International Conference on Image Processing (ICIP)",

address = "United States",

}

BLIND HIGH DYNAMIC RANGE IMAGE QUALITY ASSESSMENT USING DEEP LEARNING. / Jia, Sen; Zhang, Yang; Agrafiotis, Dimitris et al.
IEEE International Conference on Image Processing (ICIP). Institute of Electrical and Electronics Engineers (IEEE), 2018. (IEEE International Conference on Image Processing (ICIP)).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - BLIND HIGH DYNAMIC RANGE IMAGE QUALITY ASSESSMENT USING DEEP LEARNING

AU - Jia, Sen

AU - Zhang, Yang

AU - Agrafiotis, Dimitris

AU - Bull, David

PY - 2018/2/22

Y1 - 2018/2/22

N2 - In this paper we propose a No-Reference Image Quality Assessment (NR-IQA) method on High Dynamic Range (HDR) images by combining deep Convolutional Neural Networks (CNNs) with saliency maps. The proposed method utilises the power of deep CNN architectures to extract quality features which can be applied cross HDR and Standard Dynamic Range (SDR) domains. To introduce human visual system to CNNs, a saliency map algorithm is used to select a subset of salient image patches to evaluate on. Our CNN-based method delivers a state-of-the-art performance in HDR NR-IQA experiment, competitive with full reference IQA methods.

AB - In this paper we propose a No-Reference Image Quality Assessment (NR-IQA) method on High Dynamic Range (HDR) images by combining deep Convolutional Neural Networks (CNNs) with saliency maps. The proposed method utilises the power of deep CNN architectures to extract quality features which can be applied cross HDR and Standard Dynamic Range (SDR) domains. To introduce human visual system to CNNs, a saliency map algorithm is used to select a subset of salient image patches to evaluate on. Our CNN-based method delivers a state-of-the-art performance in HDR NR-IQA experiment, competitive with full reference IQA methods.

U2 - 10.1109/ICIP.2017.8296384

DO - 10.1109/ICIP.2017.8296384

M3 - Conference Contribution (Conference Proceeding)

SN - 9781509021765

T3 - IEEE International Conference on Image Processing (ICIP)

BT - IEEE International Conference on Image Processing (ICIP)

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

BLIND HIGH DYNAMIC RANGE IMAGE QUALITY ASSESSMENT USING DEEP LEARNING

Abstract

Publication series

Access to Document

Handle.net

Fingerprint

Cite this