Combined feature compression encoding in image retrieval

Authors : Lu HUO, Leijie ZHANG

Pages : 1603-1618

View : 14 | Download : 8

Publication Date : 0000-00-00

Article Type : Research Paper

Abstract :Recently, features extracted by convolutional neural networks insert ignore into journalissuearticles values(CNNs); are popularly used for image retrieval. In CNN representation, high-level features are usually chosen to represent the images in coarse-grained datasets, while mid-level features are successfully applied to describe the images for fine-grained datasets. In this paper, we combine these different levels of features as a joint feature to propose a robust representation that is suitable for both coarse-grained and fine-grained image retrieval datasets. In addition, in order to solve the problem that the efficiency of image retrieval is influenced by the dimensionality of indexing, a unified subspace learning model named spectral regression insert ignore into journalissuearticles values(SR); is applied in this paper. We combine SR and the robust representation of the CNN to form a combined feature compression encoding insert ignore into journalissuearticles values(CFCE); method. CFCE preserve the information without noticeably impacting image retrieval accuracy. We find the tendency of the image retrieval performance to change the compressed dimensionality of features. We further discover a reasonable dimensionality of indexing in image retrieval. Experiments demonstrate that our model provides state-of-the-art performances across datasets.
Keywords : Convolutional neural networks, feature selection, image retrieval, spectral regression