21 July 2017 Rotation invariant deep binary hashing for fast image retrieval
Author Affiliations +
Proceedings Volume 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017); 104201Z (2017) https://doi.org/10.1117/12.2281692
Event: Ninth International Conference on Digital Image Processing (ICDIP 2017), 2017, Hong Kong, China
Abstract
In this paper, we study how to compactly represent image’s characteristics for fast image retrieval. We propose supervised rotation invariant compact discriminative binary descriptors through combining convolutional neural network with hashing. In the proposed network, binary codes are learned by employing a hidden layer for representing latent concepts that dominate on class labels. A loss function is proposed to minimize the difference between binary descriptors that describe reference image and the rotated one. Compared with some other supervised methods, the proposed network doesn’t have to require pair-wised inputs for binary code learning. Experimental results show that our method is effective and achieves state-of-the-art results on the CIFAR-10 and MNIST datasets.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lai Dai, Jianming Liu, Aiwen Jiang, "Rotation invariant deep binary hashing for fast image retrieval", Proc. SPIE 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017), 104201Z (21 July 2017); doi: 10.1117/12.2281692; https://doi.org/10.1117/12.2281692
PROCEEDINGS
5 PAGES


SHARE
Back to Top