AUTHOR=Meng Chunli , An Ping , Huang Xinpeng , Yang Chao , Chen Yilei 

TITLE=Image Quality Evaluation of Light Field Image Based on Macro-Pixels and Focus Stack

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 15 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2021.768021

DOI=10.3389/fncom.2021.768021

ISSN=1662-5188

ABSTRACT=Light field image processing faces more opportunities and challenges than ordinary image processing due to the complex angular-spatial structure. The angular-spatial structure loss of light field images can be reflected from its various representations. The angular and spatial information penetrate each other, so it is necessary to extract appropriate features to analyze the angular-spatial structure loss of distorted light field images. In this paper, a light field image quality evaluation model, namely MPFS, is proposed based on the prediction of global angular-spatial distortion of macro pixels and the evaluation of local angular-spatial quality of the focus stack. Specifically, the angular distortion of the light field image is first evaluated through the luminance and chrominance of macro-pixels. Then we use the saliency of spatial texture structure to pool the array of predicted values of angular distortion to obtain the predicted value of global distortion. Secondly, the local angular-spatial quality of the light field image is analyzed through the principal components of the focus stack. The damaged focalizing structure caused by the angular-spatial distortion is calculated by using the features of corner structure and texture structure. Finally, the global and local angular-spatial quality evaluation models are combined to realize the evaluation of the overall quality of the light field image. Extensive comparative experiments show that the proposed method has high efficiency and precision.