Department of Computer Science, Systems and Communications, University of Milano-Bicocca, 20126 Milan, Italy.
lastminute.com Group, 6830 Chiasso, Switzerland.
Sensors (Basel). 2021 Feb 2;21(3):994. doi: 10.3390/s21030994.
We propose an anomaly detection based image quality assessment method which exploits the correlations between feature maps from a pre-trained Convolutional Neural Network (CNN). The proposed method encodes the intra-layer correlation through the Gram matrix and then estimates the quality score combining the average of the correlation and the output from an anomaly detection method. The latter evaluates the degree of abnormality of an image by computing a correlation similarity with respect to a dictionary of pristine images. The effectiveness of the method is tested on different benchmarking datasets (LIVE-itW, KONIQ, and SPAQ).
我们提出了一种基于异常检测的图像质量评估方法，该方法利用了预训练卷积神经网络（CNN）的特征图之间的相关性。所提出的方法通过 Gram 矩阵对层内相关性进行编码，然后通过计算与原始图像字典的相关性相似性来结合异常检测方法的输出估计质量分数。后者通过计算与原始图像字典的相关性相似性来评估图像的异常程度。该方法在不同的基准数据集（LIVE-itW、KONIQ 和 SPAQ）上进行了测试。
