A novel scene classification model combining ResNet based transfer learning and data augmentation with a filter

Scene classification is a significant aspect of computer vision. Convolutional neural networks (CNNs), a development of deep learning, are a well-understood tool for image classification. But training CNNs requires large-scale datasets. Transfer learning addresses this problem and produces a solution for small-scale datasets. Because scene image classification is more complex than common image classification. We propose a novel ResNet based transfer learning model utilizing multi-layer feature fusion, taking full advantage of interlayer discriminating features and fusing them for classification by softmax regression. In addition, a novel data augmentation method with a filter useful for small-scale datasets is presented. New image patches are generated by sliding block cropping of a raw image, which are then filtered to insure that the new images sufficiently represent the original categorization. Our new ResNet based transfer learning model with enhanced data augmentation is evaluated on six benchmark scene datasets (LF, OT, FP, LS, MIT67, SUN397). Extensive experimental results show that on the six datasets our method obtains better accuracy than other state-of-the-art models.