Fully Deep Blind Image Quality Predictor

Jongyoo Kim, Sanghoon Lee

Research output: Contribution to journalArticle

97 Citations (Scopus)

Abstract

In general, owing to the benefits obtained from original information, full-reference image quality assessment (FR-IQA) achieves relatively higher prediction accuracy than no-reference image quality assessment (NR-IQA). By fully utilizing reference images, conventional FR-IQA methods have been investigated to produce objective scores that are close to subjective scores. In contrast, NR-IQA does not consider reference images; thus, its performance is inferior to that of FR-IQA. To alleviate this accuracy discrepancy between FR-IQA and NR-IQA methods, we propose a blind image evaluator based on a convolutional neural network (BIECON). To imitate FR-IQA behavior, we adopt the strong representation power of a deep convolutional neural network to generate a local quality map, similar to FR-IQA. To obtain the best results from the deep neural network, replacing hand-crafted features with automatically learned features is necessary. To apply the deep model to the NR-IQA framework, three critical problems must be resolved: 1) lack of training data; 2) absence of local ground truth targets; and 3) different purposes of feature learning. BIECON follows the FR-IQA behavior using the local quality maps as intermediate targets for conventional neural networks, which leads to NR-IQA prediction accuracy that is comparable with that of state-of-the-art FR-IQA methods.

Original languageEnglish
Article number7782419
Pages (from-to)206-220
Number of pages15
JournalIEEE Journal on Selected Topics in Signal Processing
Volume11
Issue number1
DOIs
Publication statusPublished - 2017 Feb

Fingerprint

Image quality
Neural networks

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

@article{c8a860d880ad4bc2a95fddc64eba3323,
title = "Fully Deep Blind Image Quality Predictor",
abstract = "In general, owing to the benefits obtained from original information, full-reference image quality assessment (FR-IQA) achieves relatively higher prediction accuracy than no-reference image quality assessment (NR-IQA). By fully utilizing reference images, conventional FR-IQA methods have been investigated to produce objective scores that are close to subjective scores. In contrast, NR-IQA does not consider reference images; thus, its performance is inferior to that of FR-IQA. To alleviate this accuracy discrepancy between FR-IQA and NR-IQA methods, we propose a blind image evaluator based on a convolutional neural network (BIECON). To imitate FR-IQA behavior, we adopt the strong representation power of a deep convolutional neural network to generate a local quality map, similar to FR-IQA. To obtain the best results from the deep neural network, replacing hand-crafted features with automatically learned features is necessary. To apply the deep model to the NR-IQA framework, three critical problems must be resolved: 1) lack of training data; 2) absence of local ground truth targets; and 3) different purposes of feature learning. BIECON follows the FR-IQA behavior using the local quality maps as intermediate targets for conventional neural networks, which leads to NR-IQA prediction accuracy that is comparable with that of state-of-the-art FR-IQA methods.",
author = "Jongyoo Kim and Sanghoon Lee",
year = "2017",
month = "2",
doi = "10.1109/JSTSP.2016.2639328",
language = "English",
volume = "11",
pages = "206--220",
journal = "IEEE Journal on Selected Topics in Signal Processing",
issn = "1932-4553",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

Fully Deep Blind Image Quality Predictor. / Kim, Jongyoo; Lee, Sanghoon.

In: IEEE Journal on Selected Topics in Signal Processing, Vol. 11, No. 1, 7782419, 02.2017, p. 206-220.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Fully Deep Blind Image Quality Predictor

AU - Kim, Jongyoo

AU - Lee, Sanghoon

PY - 2017/2

Y1 - 2017/2

N2 - In general, owing to the benefits obtained from original information, full-reference image quality assessment (FR-IQA) achieves relatively higher prediction accuracy than no-reference image quality assessment (NR-IQA). By fully utilizing reference images, conventional FR-IQA methods have been investigated to produce objective scores that are close to subjective scores. In contrast, NR-IQA does not consider reference images; thus, its performance is inferior to that of FR-IQA. To alleviate this accuracy discrepancy between FR-IQA and NR-IQA methods, we propose a blind image evaluator based on a convolutional neural network (BIECON). To imitate FR-IQA behavior, we adopt the strong representation power of a deep convolutional neural network to generate a local quality map, similar to FR-IQA. To obtain the best results from the deep neural network, replacing hand-crafted features with automatically learned features is necessary. To apply the deep model to the NR-IQA framework, three critical problems must be resolved: 1) lack of training data; 2) absence of local ground truth targets; and 3) different purposes of feature learning. BIECON follows the FR-IQA behavior using the local quality maps as intermediate targets for conventional neural networks, which leads to NR-IQA prediction accuracy that is comparable with that of state-of-the-art FR-IQA methods.

AB - In general, owing to the benefits obtained from original information, full-reference image quality assessment (FR-IQA) achieves relatively higher prediction accuracy than no-reference image quality assessment (NR-IQA). By fully utilizing reference images, conventional FR-IQA methods have been investigated to produce objective scores that are close to subjective scores. In contrast, NR-IQA does not consider reference images; thus, its performance is inferior to that of FR-IQA. To alleviate this accuracy discrepancy between FR-IQA and NR-IQA methods, we propose a blind image evaluator based on a convolutional neural network (BIECON). To imitate FR-IQA behavior, we adopt the strong representation power of a deep convolutional neural network to generate a local quality map, similar to FR-IQA. To obtain the best results from the deep neural network, replacing hand-crafted features with automatically learned features is necessary. To apply the deep model to the NR-IQA framework, three critical problems must be resolved: 1) lack of training data; 2) absence of local ground truth targets; and 3) different purposes of feature learning. BIECON follows the FR-IQA behavior using the local quality maps as intermediate targets for conventional neural networks, which leads to NR-IQA prediction accuracy that is comparable with that of state-of-the-art FR-IQA methods.

UR - http://www.scopus.com/inward/record.url?scp=85015231355&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015231355&partnerID=8YFLogxK

U2 - 10.1109/JSTSP.2016.2639328

DO - 10.1109/JSTSP.2016.2639328

M3 - Article

AN - SCOPUS:85015231355

VL - 11

SP - 206

EP - 220

JO - IEEE Journal on Selected Topics in Signal Processing

JF - IEEE Journal on Selected Topics in Signal Processing

SN - 1932-4553

IS - 1

M1 - 7782419

ER -