Li Chaofeng, Bovik Alan Conrad, Wu Xiaojun
IEEE Trans Neural Netw. 2011 May;22(5):793-9. doi: 10.1109/TNN.2011.2120620. Epub 2011 Apr 11.
We develop a no-reference image quality assessment (QA) algorithm that deploys a general regression neural network (GRNN). The new algorithm is trained on and successfully assesses image quality, relative to human subjectivity, across a range of distortion types. The features deployed for QA include the mean value of phase congruency image, the entropy of phase congruency image, the entropy of the distorted image, and the gradient of the distorted image. Image quality estimation is accomplished by approximating the functional relationship between these features and subjective mean opinion scores using a GRNN. Our experimental results show that the new method accords closely with human subjective judgment.
我们开发了一种无参考图像质量评估（QA）算法，该算法部署了通用回归神经网络（GRNN）。新算法经过训练，并成功地相对于人类主观性评估了一系列失真类型的图像质量。用于质量评估的特征包括相位一致性图像的平均值、相位一致性图像的熵、失真图像的熵以及失真图像的梯度。使用GRNN通过逼近这些特征与主观平均意见得分之间的函数关系来完成图像质量估计。我们的实验结果表明，新方法与人类主观判断密切相符。
