
Proceedings Paper
Quantized embeddings: an efficient and universal nearest neighbor method for cloud-based image retrievalFormat | Member Price | Non-Member Price |
---|---|---|
$17.00 | $21.00 |
Paper Abstract
We propose a rate-efficient, feature-agnostic approach for encoding image features for cloud-based nearest neighbor search.
We extract quantized random projections of the image features under consideration, transmit these to the cloud server, and
perform matching in the space of the quantized projections. The advantage of this approach is that, once the underlying feature
extraction algorithm is chosen for maximum discriminability and retrieval performance (e.g., SIFT, or eigen-features),
the random projections guarantee a rate-efficient representation and fast server-based matching with negligible loss in accuracy.
Using the Johnson-Lindenstrauss Lemma, we show that pair-wise distances between the underlying feature vectors
are preserved in the corresponding quantized embeddings. We report experimental results of image retrieval on two image
databases with different feature spaces; one using SIFT features and one using face features extracted using a variant of
the Viola-Jones face recognition algorithm. For both feature spaces, quantized embeddings enable accurate image retrieval
combined with improved bit-rate efficiency and speed of matching, when compared with the underlying feature spaces.
Paper Details
Date Published: 26 September 2013
PDF: 11 pages
Proc. SPIE 8856, Applications of Digital Image Processing XXXVI, 885609 (26 September 2013); doi: 10.1117/12.2022286
Published in SPIE Proceedings Vol. 8856:
Applications of Digital Image Processing XXXVI
Andrew G. Tescher, Editor(s)
PDF: 11 pages
Proc. SPIE 8856, Applications of Digital Image Processing XXXVI, 885609 (26 September 2013); doi: 10.1117/12.2022286
Show Author Affiliations
Shantanu Rane, Mitsubishi Electric Research Labs. (United States)
Petros Boufounos, Mitsubishi Electric Research Labs. (United States)
Petros Boufounos, Mitsubishi Electric Research Labs. (United States)
Anthony Vetro, Mitsubishi Electric Research Labs. (United States)
Published in SPIE Proceedings Vol. 8856:
Applications of Digital Image Processing XXXVI
Andrew G. Tescher, Editor(s)
© SPIE. Terms of Use
