Yan, Junhua, Bai, Xuehan, Zhang, Wanyi, Xiao, Yongqi, Chatwin, Chris, Young, Rupert and Birch, Phil (2019) No-reference image quality assessment based on the AdaBoost BP neural network in the wavelet domain. Journal of Systems Engineering and Electronics, 30 (2). pp. 223-237. ISSN 1004-4132
![]() |
PDF
- Published Version
Download (5MB) |
![]() |
PDF
- Other
Restricted to SRO admin only Download (5MB) |
![]() |
PDF
- Accepted Version
Restricted to SRO admin only Download (2MB) |
Abstract
Considering the relatively poor robustness of quality scores for different types of distortion and the lack of mechanism for determining distortion types, a no-reference image quality assessment (NR-IQA) method based on the AdaBoost BP Neural Network in Wavelet domain (WABNN) is proposed. A 36-dimensional image feature vector is constructed by extracting natural scene statistics (NSS) features and local information entropy features of the distorted image wavelet sub-band coefficients in three scales. The ABNN classifier is obtained by learning the relationship between image features and distortion types. The ABNN scorer is obtained by learning the relationship between image features and image quality scores. A series of contrast experiments are carried out in the LIVE database and TID2013 database. Experimental results show the high accuracy of the distinguishing distortion type, the high consistency with subjective scores and the high robustness of the method for distorted images. Experiment results also show the independence for the database and the relatively high operation efficiency of this method.
View download statistics for this item
📧 Request an updateProject Name | Sussex Project Number | Funder | Funder Ref |
---|---|---|---|
Science and Technology on Avionics Integration Laboratory and Aeronautical Science Foundation of China (20155552050), | iisp-Visiting Fellow | National Natural Science Foundation of China (61471194; 61705104), | (61471194; 61705104), |