No-reference image quality assessment using modified extreme learning machine classifier

S. Suresh, R. Venkatesh Babu, Hyong Joong Kim

Research output: Contribution to journalArticle

184 Citations (Scopus)

Abstract

In this paper, we present a machine learning approach to measure the visual quality of JPEG-coded images. The features for predicting the perceived image quality are extracted by considering key human visual sensitivity (HVS) factors such as edge amplitude, edge length, background activity and background luminance. Image quality assessment involves estimating the functional relationship between HVS features and subjective test scores. The quality of the compressed images are obtained without referring to their original images ('No Reference' metric). Here, the problem of quality estimation is transformed to a classification problem and solved using extreme learning machine (ELM) algorithm. In ELM, the input weights and the bias values are randomly chosen and the output weights are analytically calculated. The generalization performance of the ELM algorithm for classification problems with imbalance in the number of samples per quality class depends critically on the input weights and the bias values. Hence, we propose two schemes, namely the k-fold selection scheme (KS-ELM) and the real-coded genetic algorithm (RCGA-ELM) to select the input weights and the bias values such that the generalization performance of the classifier is a maximum. Results indicate that the proposed schemes significantly improve the performance of ELM classifier under imbalance condition for image quality assessment. The experimental results prove that the estimated visual quality of the proposed RCGA-ELM emulates the mean opinion score very well. The experimental results are compared with the existing JPEG no-reference image quality metric and full-reference structural similarity image quality metric.

Original languageEnglish
Pages (from-to)541-552
Number of pages12
JournalApplied Soft Computing Journal
Volume9
Issue number2
DOIs
Publication statusPublished - 2009 Mar 1

Fingerprint

Image quality
Learning systems
Classifiers
Luminance
Genetic algorithms

Keywords

  • Blockiness measurement
  • Evolutionary algorithms
  • Extreme learning machine
  • Image quality assessment
  • JPEG
  • Neural network
  • No-reference metric

ASJC Scopus subject areas

  • Software

Cite this

No-reference image quality assessment using modified extreme learning machine classifier. / Suresh, S.; Venkatesh Babu, R.; Kim, Hyong Joong.

In: Applied Soft Computing Journal, Vol. 9, No. 2, 01.03.2009, p. 541-552.

Research output: Contribution to journalArticle

@article{b681193435304701b7122156c4379be9,
title = "No-reference image quality assessment using modified extreme learning machine classifier",
abstract = "In this paper, we present a machine learning approach to measure the visual quality of JPEG-coded images. The features for predicting the perceived image quality are extracted by considering key human visual sensitivity (HVS) factors such as edge amplitude, edge length, background activity and background luminance. Image quality assessment involves estimating the functional relationship between HVS features and subjective test scores. The quality of the compressed images are obtained without referring to their original images ('No Reference' metric). Here, the problem of quality estimation is transformed to a classification problem and solved using extreme learning machine (ELM) algorithm. In ELM, the input weights and the bias values are randomly chosen and the output weights are analytically calculated. The generalization performance of the ELM algorithm for classification problems with imbalance in the number of samples per quality class depends critically on the input weights and the bias values. Hence, we propose two schemes, namely the k-fold selection scheme (KS-ELM) and the real-coded genetic algorithm (RCGA-ELM) to select the input weights and the bias values such that the generalization performance of the classifier is a maximum. Results indicate that the proposed schemes significantly improve the performance of ELM classifier under imbalance condition for image quality assessment. The experimental results prove that the estimated visual quality of the proposed RCGA-ELM emulates the mean opinion score very well. The experimental results are compared with the existing JPEG no-reference image quality metric and full-reference structural similarity image quality metric.",
keywords = "Blockiness measurement, Evolutionary algorithms, Extreme learning machine, Image quality assessment, JPEG, Neural network, No-reference metric",
author = "S. Suresh and {Venkatesh Babu}, R. and Kim, {Hyong Joong}",
year = "2009",
month = "3",
day = "1",
doi = "10.1016/j.asoc.2008.07.005",
language = "English",
volume = "9",
pages = "541--552",
journal = "Applied Soft Computing",
issn = "1568-4946",
publisher = "Elsevier BV",
number = "2",

}

TY - JOUR

T1 - No-reference image quality assessment using modified extreme learning machine classifier

AU - Suresh, S.

AU - Venkatesh Babu, R.

AU - Kim, Hyong Joong

PY - 2009/3/1

Y1 - 2009/3/1

N2 - In this paper, we present a machine learning approach to measure the visual quality of JPEG-coded images. The features for predicting the perceived image quality are extracted by considering key human visual sensitivity (HVS) factors such as edge amplitude, edge length, background activity and background luminance. Image quality assessment involves estimating the functional relationship between HVS features and subjective test scores. The quality of the compressed images are obtained without referring to their original images ('No Reference' metric). Here, the problem of quality estimation is transformed to a classification problem and solved using extreme learning machine (ELM) algorithm. In ELM, the input weights and the bias values are randomly chosen and the output weights are analytically calculated. The generalization performance of the ELM algorithm for classification problems with imbalance in the number of samples per quality class depends critically on the input weights and the bias values. Hence, we propose two schemes, namely the k-fold selection scheme (KS-ELM) and the real-coded genetic algorithm (RCGA-ELM) to select the input weights and the bias values such that the generalization performance of the classifier is a maximum. Results indicate that the proposed schemes significantly improve the performance of ELM classifier under imbalance condition for image quality assessment. The experimental results prove that the estimated visual quality of the proposed RCGA-ELM emulates the mean opinion score very well. The experimental results are compared with the existing JPEG no-reference image quality metric and full-reference structural similarity image quality metric.

AB - In this paper, we present a machine learning approach to measure the visual quality of JPEG-coded images. The features for predicting the perceived image quality are extracted by considering key human visual sensitivity (HVS) factors such as edge amplitude, edge length, background activity and background luminance. Image quality assessment involves estimating the functional relationship between HVS features and subjective test scores. The quality of the compressed images are obtained without referring to their original images ('No Reference' metric). Here, the problem of quality estimation is transformed to a classification problem and solved using extreme learning machine (ELM) algorithm. In ELM, the input weights and the bias values are randomly chosen and the output weights are analytically calculated. The generalization performance of the ELM algorithm for classification problems with imbalance in the number of samples per quality class depends critically on the input weights and the bias values. Hence, we propose two schemes, namely the k-fold selection scheme (KS-ELM) and the real-coded genetic algorithm (RCGA-ELM) to select the input weights and the bias values such that the generalization performance of the classifier is a maximum. Results indicate that the proposed schemes significantly improve the performance of ELM classifier under imbalance condition for image quality assessment. The experimental results prove that the estimated visual quality of the proposed RCGA-ELM emulates the mean opinion score very well. The experimental results are compared with the existing JPEG no-reference image quality metric and full-reference structural similarity image quality metric.

KW - Blockiness measurement

KW - Evolutionary algorithms

KW - Extreme learning machine

KW - Image quality assessment

KW - JPEG

KW - Neural network

KW - No-reference metric

UR - http://www.scopus.com/inward/record.url?scp=58549103087&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58549103087&partnerID=8YFLogxK

U2 - 10.1016/j.asoc.2008.07.005

DO - 10.1016/j.asoc.2008.07.005

M3 - Article

AN - SCOPUS:58549103087

VL - 9

SP - 541

EP - 552

JO - Applied Soft Computing

JF - Applied Soft Computing

SN - 1568-4946

IS - 2

ER -