Deep Semantic Hashing Retrieval of Remotec Sensing Images
Cheng Chen, Huanxin Zou, Ningyuan Shao, Jiachi Sun, Xianxiang Qin · 2018
Due to the rapid evolution of satellite systems, traditional nearest neighbor image retrieval methods used in large-scale image retrieval usually cause “curse of dimensionality” that leads to boosting feature storage and slow retrieval speed. The hashing method, which aims at mapping the high-dimensional data to compact binary hash codes in Hamming space and quickly calculates the Hamming distance by bit operation and XOR operation, can effectively achieve search and retrieval with remaining similarity for big data. In this paper, we propose a novel image retrieval method based on deep hashing learning, called deep semantic hashing(DSH), attempting to mining the semantic information of remote sensing(RS) images. Experiments carried out on an archive of RS images point out that DSH outperforms other methods to achieve the state-of-the-art performance in image retrieval applications.