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 language | English |
|---|---|
| Pages (from-to) | 541-552 |
| Number of pages | 12 |
| Journal | Applied Soft Computing Journal |
| Volume | 9 |
| Issue number | 2 |
| DOIs | |
| Publication status | Published - 2009 Mar 1 |
Fingerprint
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 journal › Article
}
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 -