Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6939621 | Pattern Recognition | 2018 | 28 Pages |
Abstract
Hashing has been widely utilized for Approximate Nearest Neighbor (ANN) search due to its fast retrieval speed and low storage cost. In this work, we propose a novel supervised hashing method for scalable face image retrieval, i.e., Deep Hashing based on Classification and Quantization errors (DHCQ), by simultaneously learning feature representations of images, hash codes and classifiers. The supervised information and the deep architecture are collaboratively explored. Specifically, a deep convolutional network is introduced to learn discriminative feature representations, which are directly used to generate hash codes and predict labels of images. The quantization errors and the prediction errors jointly guide the learning of the deep network. They are highly interrelated and promoted each other. It is worth noting that the proposed method is a general hashing method and can be applied to the general image retrieval task. Extensive experiments on two face image datasets and one general image dataset demonstrate the effectiveness of the proposed method compared with several state-of-the-art hashing methods.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Jinhui Tang, Zechao Li, Xiang Zhu,