18 December 2015 Fast large-scale object retrieval with binary quantization
Author Affiliations +
J. of Electronic Imaging, 24(6), 063018 (2015). doi:10.1117/1.JEI.24.6.063018
The objective of large-scale object retrieval systems is to search for images that contain the target object in an image database. Where state-of-the-art approaches rely on global image representations to conduct searches, we consider many boxes per image as candidates to search locally in a picture. In this paper, a feature quantization algorithm called binary quantization is proposed. In binary quantization, a scale-invariant feature transform (SIFT) feature is quantized into a descriptive and discriminative bit-vector, which allows itself to adapt to the classic inverted file structure for box indexing. The inverted file, which stores the bit-vector and box ID where the SIFT feature is located inside, is compact and can be loaded into the main memory for efficient box indexing. We evaluate our approach on available object retrieval datasets. Experimental results demonstrate that the proposed approach is fast and achieves excellent search quality. Therefore, the proposed approach is an improvement over state-of-the-art approaches for object retrieval.
© 2015 SPIE and IS&T
Shifu Zhou, Dan Zeng, Wei Shen, Zhijiang Zhang, Qi Tian, "Fast large-scale object retrieval with binary quantization," Journal of Electronic Imaging 24(6), 063018 (18 December 2015). https://doi.org/10.1117/1.JEI.24.6.063018


Local spatial binary pattern a new feature descriptor for...
Proceedings of SPIE (January 10 2014)
Tools and techniques for color image retrieval
Proceedings of SPIE (March 13 1996)
A hybrid approach for face template protection
Proceedings of SPIE (March 17 2008)
An efficient approach for video information retrieval
Proceedings of SPIE (January 17 2005)

Back to Top