Abstract
We propose a blind image quality assessment that is highly unsupervised and training free. The new method is based on the hypothesis that the effect caused by distortion can be expressed by certain latent characteristics. Combined with probabilistic latent semantic analysis, the latent characteristics can be discovered by applying a topic model over a visual word dictionary. Four distortion-affected features are extracted to form the visual words in the dictionary: (1) the block-based local histogram; (2) the block-based local mean value; (3) the mean value of contrast within a block; (4) the variance of contrast within a block. Based on the dictionary, the latent topics in the images can be discovered. The discrepancy between the frequency of the topics in an unfamiliar image and a large number of pristine images is applied to measure the image quality. Experimental results for four open databases show that the newly proposed method correlates well with human subjective judgments of diversely distorted images.
Highlights
With the explosion of multimedia development, the perceptual optimization of multimedia services has gained importance
The feature extraction of the newly proposed method is based on image grayscale fluctuation (GF) analysis
The qualityaware features are taken from the obtained GF primitive map
Summary
With the explosion of multimedia development, the perceptual optimization of multimedia services has gained importance. The framework of our method mainly contains (1) feature extraction based on grayscale fluctuation (GF) (Yang et al 2014) analysis; (2) construction of a dictionary of visual words; (3) discovery of image latent distortion-affection topics via PLSA; and (4) measurement of image quality. The block-based local mean-value of pixel values in the image primitive map is chosen to represent the intensity of the GF situation in different image regions. This paper uses the block-based local histogram, the block-based local mean value, the mean value of contrast within block and the variance of contrast within block of the primitive map as four quality-aware features with which to construct an image visual dictionary.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
