These are datasets for ocean front classification. The four datasets included in the file are no-front color dataset, front color dataset, no-front grey dataset and front grey dataset, respectively. The no-front dataset is consist of sea surface temperature images that does not contain any ocean front features, and the front dataset is consist of sea surface temperature images that contain ocean front features. Further more, the no-front grey dataset only contains grey images, and the no-front color dataset only contains colorful images. So as the front grey and front color datasets.

Anyone who would use these datasets for research is suggested to cite the following papers.

这四个数据集分别是海洋表面温度灰度图像无海洋锋数据集，海洋表面温度灰度图像海洋锋数据集，海洋表面温度彩色图像无海洋锋数据集和海洋表面温度彩色图像海洋锋数据集。这些数据集用于在以下两篇论文中进行深度网络的训练，以实现基于海洋表面温度图像海洋锋的自动分类任务。任何需要使用这些数据集的个人或者机构请考虑引用下面的这两篇文章。

Lima E, Sun X, Dong J, et al. Learning and transferring convolutional neural network knowledge to ocean front recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(3): 354-358.

Lima E, Sun X, Yang Y, et al. Application of deep convolutional neural networks for ocean front recognition[J]. Journal of Applied Remote Sensing, 2017, 11(4): 042610.