Abstract
This paper proposes an image quality metric (IQM) using compressive sensing (CS) and a filter set consisting of derivative and Gabor filters. In this paper, compressive sensing that is used for acquiring a sparse or compressible signal with a small number of measurements is used for measuring the quality between the reference and distorted images. However, an image is generally neither sparse nor compressible, so a CS technique cannot be directly used for image quality assessment. Thus, for converting an image into a sparse or compressible signal, the image is convolved with filters such as the gradient, Laplacian of Gaussian, and Gabor filters, since the filter outputs are generally compressible. A small number of measurements obtained by a CS technique are used for evaluating the image quality. Experimental results with various test images show the effectiveness of the proposed algorithm in terms of the Pearson correlation coefficient (CC), root mean squared error, Spearman rank order CC, and Kendall CC.
Highlights
Objective image quality assessment (IQA) has the goal to evaluate the quality of an arbitrary image, which coincides with the subjective image quality such as the mean opinion score (MOS)
The filter set consists of the gradient, Laplacian of Gaussian (LoG), and Gabor filters used for spectral analysis [32], in which an image is analyzed via several types of filters since each filter has a unique filter response
For testing the performance of an image quality metric (IQM) obtained after fitting by logistic regression method, the fitted versions of the IQM are compared with the difference mean opinion score (DMOS), the subjective IQA method, in terms of the performance measure such as the Pearson CC, root mean square error (RMSE), Spearman rank order CC (SROCC) and Kendall CC, which were recommended by video quality expert group (VQEG) [43] and used in [38]
Summary
Objective image quality assessment (IQA) has the goal to evaluate the quality of an arbitrary image, which coincides with the subjective image quality such as the mean opinion score (MOS). The MOS represents the image quality that follows the human visual perception. The closer to the subjective IQA an objective IQA is, the better the image quality metric is. Objective IQA algorithms are classified into three approaches according to the type of information used: structure, human perception/visual attention, and information theory. In this paper, we adopt a new concept for assessing the image quality. We present a new image quality metric (IQM) using CS and a filter set.
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 callMore From: Advances in Vision Computing: An International Journal
Disclaimer: 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.
