arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.10753cs.CVcs.NAeess.IVmath.NA
收藏

基于Cahn-Hilliard图像修补的破损图像预测增强

Enhancement of damaged-image prediction through Cahn-Hilliard Image Inpainting

Mathematical Institute, University of Oxford(牛津大学数学研究所);Imperial College London(帝国理工学院)

José A. Carrillo, Serafim Kalliadasis, Fuyue Liang, Sergio P. Perez

摘要:

我们评估的好处,包括一个图像修补过滤器之前,通过损坏的图像到一个分类神经网络。为此,我们采用修改后的Cahn-Hilliard方程作为图像修补过滤器,这是通过有限体积方案,减少计算成本和足够的性能的能量稳定性和有界性。这里采用的基准数据集是MNIST,它由手写数字的二进制图像组成,是验证图像处理方法的标准数据集。我们用MNIST的训练集训练一个基于稠密层的神经网络,然后用不同类型和强度的损伤污染测试集。然后,我们比较的预测精度的神经网络与不适用于Cahn-Hilliard滤波器的损坏的图像测试。我们的研究结果量化了由于应用Cahn-Hilliard滤波器而导致的损坏图像预测的显着改善,对于特定的损坏,该滤波器可以增加高达50%,并且通常对于低到中等的损坏是有利的。

英文摘要:

We assess the benefit of including an image inpainting filter before passing damaged images into a classification neural network. For this we employ a modified Cahn-Hilliard equation as an image inpainting filter, which is solved via a finite volume scheme with reduced computational cost and adequate properties for energy stability and boundedness. The benchmark dataset employed here is MNIST, which consists of binary images of handwritten digits and is a standard dataset to validate image-processing methodologies. We train a neural network based of dense layers with the training set of MNIST, and subsequently we contaminate the test set with damage of different types and intensities. We then compare the prediction accuracy of the neural network with and without applying the Cahn-Hilliard filter to the damaged images test. Our results quantify the significant improvement of damaged-image prediction due to applying the Cahn-Hilliard filter, which for specific damages can increase up to 50% and is in general advantageous for low to moderate damage.

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。

↑