Feature Extraction with Convolutional Neural Networks for Aerial Image Retrieval

Deep learning methods have been effectively used to provide great improvement in various research fields such as machine learning, image processing and computer vision. One of the most frequently used deep learning methods in image processing is the convolutional neural networks. Compared to the traditional artificial neural networks, convolutional neural networks do not use the predefined kernels, but instead they learn data specific kernels. This property makes them to be used as feature extractors as well. In this study, we used a convolutional neural network including 60 million parameters and 650 thousand neurons to extract features to be used for image retrieval. The architecture of the network consists of five convolutional layers and three fully-connected layers. Extracted features, in comparison with Fisher vectors - which are one of the most widely used representation types - are tested on UCMerced Land Use dataset in terms of retrieval accuracies by using different hashing methods. Experimental results demostrate the superiority of the CNN features.