arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.06911cs.CV
收藏

图像质量评价算法的选择

Algorithm Selection for Image Quality Assessment

University of Adelaide(阿德莱德大学);University of Konstanz(康斯坦茨大学);University of Kent(肯特大学)

Markus Wagner, Hanhe Lin, Shujun Li, Dietmar Saupe

摘要:

主观感知图像质量可以在实验室研究中由人类观察者评估。客观图像质量评估(IQA)是指用于估计平均主观质量评级的算法。已经提出了许多这样的方法,无论是盲IQA,其中没有原始参考图像是可用的,以及为全参考的情况下。我们比较了8个最先进的盲IQA算法,并表明,一个预言机,能够预测任何给定的输入图像的最佳性能的方法,产生一个混合的方法,甚至可以优于最好的单一现有方法的大幅度。在这方面的贡献,我们解决的研究问题是否建立的方法来学习这样一个预言可以提高盲IQA。我们应用了AutoFolio,这是一个最先进的系统,可以训练算法选择器为给定实例选择性能良好的算法。我们还训练了深度神经网络来预测最佳方法。我们的研究结果没有给出肯定的答案,算法选择并没有产生比单一最佳方法显著的改善。深入研究结果,我们观察到图像中的噪声可能在我们训练的分类器无法预测预言的原因中发挥了作用。这激发了IQA方法中对噪声的考虑,这是一种迄今为止尚未观察到的属性,它开辟了几个有趣的新研究问题和应用。

英文摘要:

Subjective perceptual image quality can be assessed in lab studies by human observers. Objective image quality assessment (IQA) refers to algorithms for estimation of the mean subjective quality ratings. Many such methods have been proposed, both for blind IQA in which no original reference image is available as well as for the full-reference case. We compared 8 state-of-the-art algorithms for blind IQA and showed that an oracle, able to predict the best performing method for any given input image, yields a hybrid method that could outperform even the best single existing method by a large margin. In this contribution we address the research question whether established methods to learn such an oracle can improve blind IQA. We applied AutoFolio, a state-of-the-art system that trains an algorithm selector to choose a well-performing algorithm for a given instance. We also trained deep neural networks to predict the best method. Our results did not give a positive answer, algorithm selection did not yield a significant improvement over the single best method. Looking into the results in depth, we observed that the noise in images may have played a role in why our trained classifiers could not predict the oracle. This motivates the consideration of noisiness in IQA methods, a property that has so far not been observed and that opens up several interesting new research questions and applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑