Content-based image retrieval based on CNN and SVM
Ruigang Fu, Biao Li, Yinghui Gao, Ping Wang · 2016
The retrieval performance of a content-based image retrieval (CBIR) system is mainly influenced by the feature representations and similarity measures. Recently, deep learning develops rapidly and the deep features based on deep learning have been applied widely because it has been shown that the features have very strong generalization. This paper applies the original deep features generated by convolution neural network (CNN) to CBIR, and uses linear support victor machine (SVM) to train a hyerplane which can separate similar image pairs and dissimilar image pairs to a large degree. The input of the SVM in this paper is pair features which are assembled by pair of images: the query image and each test image in the image dataset. The test images then are ranked by the distance between the pair features and the trained hyperplane. Experiments show that our method can significantly improve the performance of CBIR for object image retrieval tasks.