Blind Image Quality Assessment Based on Multichannel Feature Fusion and Label Transfer

• Published in: IEEE transactions on circuits and systems for video technology Vol. 26; no. 3; pp. 425 - 440
• Main Authors: Qingbo Wu, Hongliang Li, Fanman Meng, Ngan, King N., Luo, Bing, Huang, Chao, Zeng, Bing
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.03.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Assessments; BIQA; Blinds; Channels; Discrete cosine transform; Discrete cosine transforms; Domains; Entropy; Feature extraction; Image color analysis; Image management; Image quality; Image retrieval; Label Transfer; Labels; Mathematical models; Multi-channel features fusion; Performance evaluation; Prediction models; Quality; Quality assessment; Visualization; Wavelet analysis; Wavelet domain; label transfer (LT); multichannel features fusion; Blind image quality assessment (BIQA)
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2015.2412773

In this paper, we propose an efficient blind image quality assessment (BIQA) algorithm, which is characterized by a new feature fusion scheme and a k-nearest-neighbor (KNN)-based quality prediction model. Our goal is to predict the perceptual quality of an image without any prior information of its reference image and distortion type. Since the reference image is inaccessible in many applications, the BIQA is quite desirable in this context. In our method, a new feature fusion scheme is first introduced by combining an image's statistical information from multiple domains (i.e., discrete cosine transform, wavelet, and spatial domains) and multiple color channels (i.e., Y, Cb, and Cr). Then, the predicted image quality is generated from a nonparametric model, which is referred to as the label transfer (LT). Based on the assumption that similar images share similar perceptual qualities, we implement the LT with an image retrieval procedure, where a query image's KNNs are searched for from some annotated images. The weighted average of the KNN labels (e.g., difference mean opinion score or mean opinion score) is used as the predicted quality score. The proposed method is straightforward and computationally appealing. Experimental results on three publicly available databases (i.e., LIVE II, TID2008, and CSIQ) show that the proposed method is highly consistent with human perception and outperforms many representative BIQA metrics.