Sciweavers

WACV
2012
IEEE

CompactKdt: Compact signatures for accurate large scale object recognition

12 years 7 months ago
CompactKdt: Compact signatures for accurate large scale object recognition
We present a novel algorithm, Compact Kd-Trees (CompactKdt), that achieves state-of-the-art performance in searching large scale object image collections. The algorithm uses an order of magnitude less storage and computations by making use of both the full local features (e.g. SIFT) and their compact binary signatures to build and search the K-Tree. We compare classical PCA dimensionality reduction to three methods for generating compact binary representations for the features: Spectral Hashing, Locality Sensitive Hashing, and Locality Sensitive Binary Codes. CompactKdt achieves significant performance gain over using the binary signatures alone, and comparable performance to using the full features alone. Finally, our experiments show significantly better performance than the state-of-the-art Bag of Words (BoW) methods with equivalent or less storage and computational cost.
Mohamed Aly, Mario E. Munich, Pietro Perona
Added 25 Apr 2012
Updated 25 Apr 2012
Type Journal
Year 2012
Where WACV
Authors Mohamed Aly, Mario E. Munich, Pietro Perona
Comments (0)