Name
Abstract | ||
|---|---|---|
Local features are widely used for content-based image retrieval and object recognition. We present an efficient method for encoding digital images suitable for local feature extraction. First, we find the patches in the image corresponding to the detected features. Then, we extract these patches at their characteristic scale and orientation and encode them for efficient transmission. A Discrete Cosine Transform (DCT) with adaptive block size is used for patch compression. We compare this method to directly compressing feature descriptors using transform coding. Experimental results show the superior performance of our technique. Image patches can be compressed to rates around 55 bits/patch (18times compression relative to uncompressed SIFT feature descriptors) and still achieve good image matching performance. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/ICASSP.2009.4959710 | ICASSP |
Keywords | Field | DocType |
uncompressed sift feature descriptors,image coding,image matching,index terms— image compression,feature descriptors,good image,discrete cosine transform,image compression,data compression,transform coding,discrete cosine transforms,image patch,content-based image retrieval,feature extraction,image retrieval,image patches compression,object recognition,compressing feature,efficient transmission,digital image,efficient method,local feature,content-based retrieval,local feature extraction,digital images,probability density function,databases,indexing terms,computer vision | Computer vision,Feature detection (computer vision),Pattern recognition,Feature (computer vision),Computer science,Discrete cosine transform,Transform coding,Feature extraction,Artificial intelligence,Data compression,Content-based image retrieval,Image compression | Conference |
ISSN | ISBN | Citations |
1520-6149 E-ISBN : 978-1-4244-2354-5 | 978-1-4244-2354-5 | 30 |
PageRank | References | Authors |
1.50 | 8 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mina Makar | 1 | 93 | 7.27 |
| Chuo-Ling Chang | 2 | 247 | 18.15 |
| David Chen | 3 | 40 | 2.09 |
| Sam S. Tsai | 4 | 724 | 36.51 |
| Bernd Girod | 5 | 8988 | 1062.96 |