J Opt Soc Am A Opt Image Sci Vis. 2022 Jun 1;39(6):B1-B10. doi: 10.1364/JOSAA.448144.
Blind image quality assessment (BIQA) of authentically distorted images is a challenging problem due to the lack of a reference image and the coexistence of blends of distortions with unknown characteristics. In this article, we present a convolutional neural network based BIQA model. It encodes the input image into multi-level features to estimate the perceptual quality score. The proposed model is designed to predict the image quality score but is trained for jointly treating the image quality assessment as a classification, regression, and pairwise ranking problem. Experimental results on three different datasets of authentically distorted images show that the proposed method achieves comparable results with state-of-the-art methods in intra-dataset experiments and is more effective in cross-dataset experiments.
由于缺乏参考图像以及未知特征的失真混合，真实失真图像的盲图像质量评估（BIQA）是一个具有挑战性的问题。在本文中，我们提出了一种基于卷积神经网络的 BIQA 模型。它将输入图像编码为多层次特征，以估计感知质量评分。所提出的模型旨在预测图像质量评分，但同时也将图像质量评估作为分类、回归和成对排序问题进行联合处理。在三个不同的真实失真图像数据集上的实验结果表明，该方法在数据集内实验中与最先进的方法取得了可比的结果，并且在跨数据集实验中更为有效。
