TY - GEN
T1 - Analysis of global spatial statistics features in existing contrast image quality assessment algorithm
AU - Ahmed, Ismail Taha
AU - Der, Chen Soong
AU - Jamil, Norziana
AU - Hammad, Baraa Tareq
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/7
Y1 - 2019/7
N2 - Most of existing image quality assessment algorithms (IQAs) have been developed during the past decade. However, most of them are designed for images distorted by compression, noise and blurring. There are very few IQAs designed specifically for CDI, e.g. Contrast distortion may be caused by poor lighting condition and poor-quality image acquisition device. No Reference-Image Quality Assessment (NR-IQA) for Contrast-Distorted Images (NR-IQA-CDI) is one of these few IQAs. The five features used in NR-IQA-CDI are the global spatial statistics of an image including the mean, standard deviation, entropy, kurtosis and skewness. Unfortunately, the performance of NR-IQA-CDI are not encouraging in two of the three test image databases, TID2013 and CSIQ, where the Pearson Linear Correlation Coefficients are only around 0.57 and 0.76, respectively. Therefore, this paper presents the reason which led to poor results in existing NR-IQA-CDI. This paper also can address the problem of existing NR-IQA-CDI which the weakness of the global features in assessing images with uneven contrast.
AB - Most of existing image quality assessment algorithms (IQAs) have been developed during the past decade. However, most of them are designed for images distorted by compression, noise and blurring. There are very few IQAs designed specifically for CDI, e.g. Contrast distortion may be caused by poor lighting condition and poor-quality image acquisition device. No Reference-Image Quality Assessment (NR-IQA) for Contrast-Distorted Images (NR-IQA-CDI) is one of these few IQAs. The five features used in NR-IQA-CDI are the global spatial statistics of an image including the mean, standard deviation, entropy, kurtosis and skewness. Unfortunately, the performance of NR-IQA-CDI are not encouraging in two of the three test image databases, TID2013 and CSIQ, where the Pearson Linear Correlation Coefficients are only around 0.57 and 0.76, respectively. Therefore, this paper presents the reason which led to poor results in existing NR-IQA-CDI. This paper also can address the problem of existing NR-IQA-CDI which the weakness of the global features in assessing images with uneven contrast.
KW - Contrast-distorted image (CDI)
KW - Global spatial statistics
KW - Local spatial statistics
KW - No Reference-Image Quality Assessment (NR-IQA) for Contrast-Distorted Images (NR-IQA-CDI)
KW - Uneven Contrast
UR - http://www.scopus.com/inward/record.url?scp=85073192228&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85073192228&partnerID=8YFLogxK
U2 - 10.1109/ICoICT.2019.8835319
DO - 10.1109/ICoICT.2019.8835319
M3 - Conference contribution
AN - SCOPUS:85073192228
T3 - 2019 7th International Conference on Information and Communication Technology, ICoICT 2019
BT - 2019 7th International Conference on Information and Communication Technology, ICoICT 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th International Conference on Information and Communication Technology, ICoICT 2019
Y2 - 24 July 2019 through 26 July 2019
ER -