An effective general-purpose NR-IQA model using natural scene statistics (NSS) of the luminance relative order

International audienceBlind/no-reference image quality assessment (NR-IQA) aims to assess the quality of an image without any reference image. In this paper, we propose an effective and efficient general-purpose NR-IQA model using natural scene statistics (NSS) of the luminance relative order, based on the observation that the variation of the marginal distribution of the relative order coefficients effectively reflect the degree of warping caused by different types of image distortions. In the literature, gradient-relevant methods have had a big success in full-reference (FR) IQA and reduced-reference (RR) IQA. Inspired by these, we extend it to NR-IQA in this paper. Notice that the NSS-based models usually extract their features derived from the spatial, wavelet, DCT and spectral domain etc. Unlike these metrics, the proposed method firstly extracts 32 natural scene statistics features of the luminance relative order, obtained from the log histograms of log horizontal, vertical, main-diagonal and secondary-diagonal derivatives, along with kurtosis, variance, differential entropy and entropy at two scales. Then a mapping is learned to predict the quality score using a support vector regression. The experimental results on several benchmark databases showed that the proposed method is comparable with the state-of-the-art methods and has a relatively low complexity. I Image quality assessment (IQA) is involved in numerous fields and applications since it is essential for the comparison and the optimization of different image processing methods. In many image processing tasks (e.g., image acquisition, compression, restoration, transmission, etc.), it is necessary to assess the quality of the output image. The end-user of images is human; thus the subjective assessment is always the ultimate and the most reliable test. However, the subjective assessment is time-consuming, expensive and cannot be real-time. That is why objective methods mimicking human perception have been developed to assess the perceived quality automatically. Objective methods can be divided into three categories depending on the amount of accessible information: full-reference (FR), reduced-reference (RR) and no-reference (NR). The FR IQA metric needs an ideal "reference" image, e.g. SSIM [1], ESSIM [2] and [24]. However, the reference image is not always available. Instead of utilizing the full information from the reference image, the RR metric [23] compares the distorted image and the reference one based on a short description (e.g. extracted features) of the reference image, which is transmitted along with the distorted image. The deployment of the RR metric is difficult since most operators refuse to pay this additional transmission cost for the non-visible information. The NR IQA metric blindly evaluates the distorted image quality, without any reference image. This could be very useful for the applications without reference image or with limited bandwidth. The NR-IQA metrics can further be classified into two types: distortion-specific (DS) and general-purpose. The DS metrics aim at some specific distortion(s) and must have some a priori information about the distortion(s) [3-5]. The general-purpose metrics aim to tackle different types of distortion [6-21]. This paper focuses on the general-purpose NR-IQA metrics, which may have a single-stage or two-stage framework. For a two-stage framework metric, the number of distortion types should be known