Multiple Level Feature-Based Universal Blind Image Quality Assessment Model

Jongyoo Kim; Anh Duc Nguyen; Sewoong Ahn; Chong Luo; Sanghoon Lee

doi:10.1109/ICIP.2018.8451346

Multiple Level Feature-Based Universal Blind Image Quality Assessment Model

Jongyoo Kim, Anh Duc Nguyen, Sewoong Ahn, Chong Luo, Sanghoon Lee

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

24 Citations (Scopus)

Abstract

The direct use of a deep convolutional neural network (CNN) in no-reference image quality assessment (NR-IQA) usually struggles for a good performance due to a lack of training data, which can be alleviated by transfer learning. However, depending on the similarity between the source and target tasks, the final performance differs vastly. In particular, various kinds of distortion types exist in IQA, which requires different kinds of features to predict visual quality. In this paper, to make the transferred model robust to various distortion types, we propose a Multiple-level Feature-based Image Quality Assessor (MFIQA) which considers multiple levels of features simultaneously. Through rigorous experiments, we prove that MFIQA consistently yields state-of-the-art performance regardless of the distortion types including synthetic and authentic corruption.

Original language	English
Title of host publication	2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
Publisher	IEEE Computer Society
Pages	291-295
Number of pages	5
ISBN (Electronic)	9781479970612
DOIs	https://doi.org/10.1109/ICIP.2018.8451346
Publication status	Published - 2018 Aug 29
Event	25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece Duration: 2018 Oct 7 → 2018 Oct 10

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
ISSN (Print)	1522-4880

Conference

Conference	25th IEEE International Conference on Image Processing, ICIP 2018
Country/Territory	Greece
City	Athens
Period	18/10/7 → 18/10/10

Bibliographical note

Funding Information:
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2016R1A2B2014525).

Publisher Copyright:
© 2018 IEEE.

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP.2018.8451346

Cite this

Kim, J., Nguyen, A. D., Ahn, S., Luo, C., & Lee, S. (2018). Multiple Level Feature-Based Universal Blind Image Quality Assessment Model. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings (pp. 291-295). [8451346] (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP.2018.8451346

@inproceedings{541a3b23602f428c8199b468137f037b,

title = "Multiple Level Feature-Based Universal Blind Image Quality Assessment Model",

abstract = "The direct use of a deep convolutional neural network (CNN) in no-reference image quality assessment (NR-IQA) usually struggles for a good performance due to a lack of training data, which can be alleviated by transfer learning. However, depending on the similarity between the source and target tasks, the final performance differs vastly. In particular, various kinds of distortion types exist in IQA, which requires different kinds of features to predict visual quality. In this paper, to make the transferred model robust to various distortion types, we propose a Multiple-level Feature-based Image Quality Assessor (MFIQA) which considers multiple levels of features simultaneously. Through rigorous experiments, we prove that MFIQA consistently yields state-of-the-art performance regardless of the distortion types including synthetic and authentic corruption.",

author = "Jongyoo Kim and Nguyen, {Anh Duc} and Sewoong Ahn and Chong Luo and Sanghoon Lee",

note = "Funding Information: This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2016R1A2B2014525). Publisher Copyright: {\textcopyright} 2018 IEEE.; 25th IEEE International Conference on Image Processing, ICIP 2018 ; Conference date: 07-10-2018 Through 10-10-2018",

year = "2018",

month = aug,

day = "29",

doi = "10.1109/ICIP.2018.8451346",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "291--295",

booktitle = "2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings",

address = "United States",

}

Kim, J, Nguyen, AD, Ahn, S, Luo, C & Lee, S 2018, Multiple Level Feature-Based Universal Blind Image Quality Assessment Model. in 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings., 8451346, Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 291-295, 25th IEEE International Conference on Image Processing, ICIP 2018, Athens, Greece, 18/10/7. https://doi.org/10.1109/ICIP.2018.8451346

Multiple Level Feature-Based Universal Blind Image Quality Assessment Model. / Kim, Jongyoo; Nguyen, Anh Duc; Ahn, Sewoong et al.
2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. p. 291-295 8451346 (Proceedings - International Conference on Image Processing, ICIP).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Multiple Level Feature-Based Universal Blind Image Quality Assessment Model

AU - Kim, Jongyoo

AU - Nguyen, Anh Duc

AU - Ahn, Sewoong

AU - Luo, Chong

AU - Lee, Sanghoon

N1 - Funding Information: This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2016R1A2B2014525). Publisher Copyright: © 2018 IEEE.

PY - 2018/8/29

Y1 - 2018/8/29

N2 - The direct use of a deep convolutional neural network (CNN) in no-reference image quality assessment (NR-IQA) usually struggles for a good performance due to a lack of training data, which can be alleviated by transfer learning. However, depending on the similarity between the source and target tasks, the final performance differs vastly. In particular, various kinds of distortion types exist in IQA, which requires different kinds of features to predict visual quality. In this paper, to make the transferred model robust to various distortion types, we propose a Multiple-level Feature-based Image Quality Assessor (MFIQA) which considers multiple levels of features simultaneously. Through rigorous experiments, we prove that MFIQA consistently yields state-of-the-art performance regardless of the distortion types including synthetic and authentic corruption.

AB - The direct use of a deep convolutional neural network (CNN) in no-reference image quality assessment (NR-IQA) usually struggles for a good performance due to a lack of training data, which can be alleviated by transfer learning. However, depending on the similarity between the source and target tasks, the final performance differs vastly. In particular, various kinds of distortion types exist in IQA, which requires different kinds of features to predict visual quality. In this paper, to make the transferred model robust to various distortion types, we propose a Multiple-level Feature-based Image Quality Assessor (MFIQA) which considers multiple levels of features simultaneously. Through rigorous experiments, we prove that MFIQA consistently yields state-of-the-art performance regardless of the distortion types including synthetic and authentic corruption.

UR - http://www.scopus.com/inward/record.url?scp=85058865578&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058865578&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2018.8451346

DO - 10.1109/ICIP.2018.8451346

M3 - Conference contribution

AN - SCOPUS:85058865578

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 291

EP - 295

BT - 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings

PB - IEEE Computer Society

T2 - 25th IEEE International Conference on Image Processing, ICIP 2018

Y2 - 7 October 2018 through 10 October 2018

ER -

Multiple Level Feature-Based Universal Blind Image Quality Assessment Model

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this