The spectral hashing algorithm relaxes and solves an objective function for generating hash codes such that data similarity is preserved in the Hamming space. However, the assumption of uniform global data distribution limits its applicability. In the paper, we introduce locality preserving projection to determine the data distribution adaptively, and a spectral method is adopted to estimate the eigenfunctions of the underlying graph Laplacian. Furthermore, pairwise label similarity can be further incorporated in the weight matrix to bridge the semantic gap between data and hash codes. Experiments on three benchmark datasets show the proposed algorithm performs favorably against state-of-the-art hashing methods.
|Title of host publication||2014 IEEE International Conference on Image Processing, ICIP 2014|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||5|
|Publication status||Published - 2014 Jan 28|
|Name||2014 IEEE International Conference on Image Processing, ICIP 2014|
Bibliographical notePublisher Copyright:
© 2014 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition