Abstract | ||
---|---|---|
MPEG is currently developing a standard titled Compact Descriptors for Visual Search (CDVS) for descriptor extraction and compression. In this work, we report comprehensive patch-level experiments for a direct comparison of low bitrate descriptors for visual search. For evaluating different compression schemes, we propose a dataset of matching pairs of image patches from the MPEG-CDVS image-level data sets. We propose a greedy rate allocation scheme for distributing bits across different spatialbins of the SIFT descriptor. We study a scheme based on Entropy Constrained Vector Quantization and greedy rate allocation, which performs close to the performancebound for any compression scheme. Finally, we present extensive feature-level Receiver Operating Characteristic (ROC) comparisons for different compression schemes (VectorQuantization, Transform Coding, Lattice Coding) proposed during the MPEG-CDVS standardization process. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/DCC.2014.50 | Data Compression Conference |
Keywords | Field | DocType |
entropy,feature extraction,greedy algorithms,image coding,image matching,image retrieval,sensitivity analysis,vector quantisation,visual perception,MPEG-CDVS image level data sets,SIFT descriptor,bits distribution,compact descriptors for visual search,comprehensive patch level experiment,descriptor compression,descriptor extraction,entropy constrained vector quantization,feature level ROC,feature matching performance,greedy rate allocation scheme,image patch matching pairs,receiver operating characteristic,spatial bins,feature compression | Computer vision,Scale-invariant feature transform,Pattern recognition,Computer science,Image retrieval,Transform coding,Coding (social sciences),Feature extraction,Greedy algorithm,Vector quantization,Artificial intelligence,Encoding (memory) | Conference |
ISSN | Citations | PageRank |
1068-0314 | 7 | 0.44 |
References | Authors | |
7 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chandrasekhar, V. | 1 | 7 | 0.44 |
Takacs, G. | 2 | 127 | 7.55 |
Chen, D.M. | 3 | 33 | 1.51 |
Sam S. Tsai | 4 | 724 | 36.51 |