TY - GEN
T1 - A Pre-Saliency Map Based Blind Image Quality Assessment via Convolutional Neural Networks
AU - Cheng, Zhengxue
AU - Takeuchi, Masaru
AU - Katto, Jiro
N1 - Funding Information:
Experimental results demonstrate that our proposed method can achieve high accuracy (0.978) with subjective quality scores, which outperforms existing IQA methods. Besides, our method achieves 52.7% time reduction compared to the IQA without saliency map. ACKNOWLEDGMENT This work was supported in part by the ”Graduate Program for Embodiment Informatics” of the Ministry of Education, Culture, Sports, Science and Technology.
Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/28
Y1 - 2017/12/28
N2 - In recent years, various approaches have been investigated towards blind image quality assessment (IQA) with high accuracy and low complexity. In this paper we develop a pre-saliency map based blind IQA method, which takes advantage of saliency information in prior of quality prediction for performance enhancement by two steps. 1) We split the image into patches and design a convolution neural network (CNN) to predict the patch-wise quality score. Then we explore the relation between image saliency information and CNN prediction error to present a statistical analysis. 2) Based on the analysis, we propose a patch quality aggregation algorithm by removing non-salient patches which are likely to bring large prediction error and assigning large weights for salient patches. Experimental results validate that our method can achieve high accuracy (0.978) with subjective quality scores, which outperforms existing IQA methods. Meanwhile, the proposed method can reduce 52.7% computational time than the IQA without pre-saliency map.
AB - In recent years, various approaches have been investigated towards blind image quality assessment (IQA) with high accuracy and low complexity. In this paper we develop a pre-saliency map based blind IQA method, which takes advantage of saliency information in prior of quality prediction for performance enhancement by two steps. 1) We split the image into patches and design a convolution neural network (CNN) to predict the patch-wise quality score. Then we explore the relation between image saliency information and CNN prediction error to present a statistical analysis. 2) Based on the analysis, we propose a patch quality aggregation algorithm by removing non-salient patches which are likely to bring large prediction error and assigning large weights for salient patches. Experimental results validate that our method can achieve high accuracy (0.978) with subjective quality scores, which outperforms existing IQA methods. Meanwhile, the proposed method can reduce 52.7% computational time than the IQA without pre-saliency map.
KW - Blind image quality assessment
KW - Convolutional neural network
KW - Pre-saliency map
UR - http://www.scopus.com/inward/record.url?scp=85045911888&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85045911888&partnerID=8YFLogxK
U2 - 10.1109/ISM.2017.21
DO - 10.1109/ISM.2017.21
M3 - Conference contribution
AN - SCOPUS:85045911888
T3 - Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017
SP - 77
EP - 82
BT - Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 19th IEEE International Symposium on Multimedia, ISM 2017
Y2 - 11 December 2017 through 13 December 2017
ER -