LAUSR

Currently, due to the exponential growth of online images, it is necessary to consider image retrieval among large number of images, which is very time-consuming and unscalable. Although many hashing methods has been proposed, they did not show excellent performance in decreasing semantic loss during the process of hashing. In this paper, we propose a novel Deep Linear Discriminant Analysis Hashing(DLDAH) algorithm, which consists of Hash label generation stage and Deep hash model construction stage. In hash label generation stage, using extract image features, we construct an objective function based on Linear Discriminant Analysis(LDA), and minimize it to map image features into hash labels. In deep hash model construction stage, we use the generated hash labels to train a simple deep learning network for image hashing and get discriminative hash codes corresponding to training images. Then the deep hash model is used to map a new image feature into hash code for fast image retrieval. The scheme obtain a deep hash model which obtains deep semantic information without using network with a lot of layers, simplifying the process of mapping new images into hash codes. Experimental results show that our approach significantly outperforms state-of-art methods.