arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.11300cs.NEcs.CVcs.LG
收藏

CoInGP:基于遗传编程的卷积图像修复

CoInGP: Convolutional Inpainting with Genetic Programming

Faculty of Electrical Engineering and Computing, University of Zagreb(萨格勒布大学电气工程与计算学院);Dipartimento di Matematica e Geoscienze, Università degli Studi di Trieste(的里雅斯特大学数学与地球科学系);Cyber Security Research Group, Delft University of Technology(代尔夫特理工大学网络安全研究组);NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa(新里斯本大学NOVA信息管理学院)

Domagoj Jakobovic, Luca Manzoni, Luca Mariot, Stjepan Picek, Mauro Castelli

摘要:

我们研究使用遗传编程(GP)作为图像中丢失像素的卷积预测器。通过在图像上扫描滑动窗口来执行训练阶段,其中边界上的像素表示GP树的输入。树的输出被作为中心像素的预测值。我们考虑两种拓扑结构的滑动窗口,即摩尔和冯诺依曼附近。然后使用在训练集上获得最低预测误差的最佳GP树来预测测试集中的像素。我们通过两个实验来评估我们的方法。在第一个中,我们训练了一个GP树的子集的1000个完整的图像从MNIST数据集。结果表明,GP可以学习像素的分布相对于一个简单的基线预测,没有显着差异之间观察到的两个邻域。在第二个实验中,我们在两张退化图像上训练GP卷积预测器,去除了大约20%的像素。在这种情况下,我们观察到摩尔邻域的效果更好,尽管冯诺依曼邻域允许更大的训练集。

英文摘要:

We investigate the use of Genetic Programming (GP) as a convolutional predictor for missing pixels in images. The training phase is performed by sweeping a sliding window over an image, where the pixels on the border represent the inputs of a GP tree. The output of the tree is taken as the predicted value for the central pixel. We consider two topologies for the sliding window, namely the Moore and the Von Neumann neighborhood. The best GP tree scoring the lowest prediction error over the training set is then used to predict the pixels in the test set. We experimentally assess our approach through two experiments. In the first one, we train a GP tree over a subset of 1000 complete images from the MNIST dataset. The results show that GP can learn the distribution of the pixels with respect to a simple baseline predictor, with no significant differences observed between the two neighborhoods. In the second experiment, we train a GP convolutional predictor on two degraded images, removing around 20% of their pixels. In this case, we observe that the Moore neighborhood works better, although the Von Neumann neighborhood allows for a larger training set.

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。

↑