Light Field Image Quality Assessment via the Light Field Coherence

Abstract

In this paper, a novel full-reference <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">image quality assessment</i> (IQA) method for evaluating the quality of the distorted <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">light field</i> (LF) image against its reference LF image is proposed, called the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">log-Gabor feature-based</i> light field coherence (LGF-LFC). Based on the fact that to compare two LF images, it essentially boils down to measure how <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">coherent</i> of these two LF images, we attempt to measure the degree of their LF <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">coherence</i> (LFC). To pursue this goal, the salient features from the reference and distorted LF images under comparison need to be extracted. By considering that the Gabor feature has the ability to well characterize the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">human visual system</i> (HVS) perception, and the special characteristics of the LF images, the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">multi</i> -scale and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">single</i> -scale Gabor feature extraction schemes are developed to extract the multi-scale log-Gabor features from the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">sub-aperture images</i> (SAIs) and the single-scale log-Gabor feature from the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">epi-polar images</i> (EPIs), respectively. Note that the former can reflect the image details (via the SAIs), while the latter indicates the viewing consistency (via the EPI’s depth information). The similarity measurements are subsequently conducted on the comparison of their SAIs and that of their EPIs separately, followed by combining them together for arriving at the final score. Extensive simulation results have clearly demonstrated that the proposed LGF-LFC is more consistent with the perception of the HVS on the quality evaluation of the LF images than multiple classical and state-of-the-art IQA methods.

Topics & Concepts