Similarity Search in High Dimensions via Hashing
VLDB '99 Proceedings of the 25th International Conference on Very Large Data Bases
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Learning task-specific similarity
Learning task-specific similarity
Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions
Communications of the ACM - 50th anniversary issue: 1958 - 2008
Faster and Better: A Machine Learning Approach to Corner Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Discriminative Learning of Local Image Descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence
Product Quantization for Nearest Neighbor Search
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning Linear Discriminant Projections for Dimensionality Reduction of Image Descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence
LDAHash: Improved Matching with Smaller Descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence
SURF: speeded up robust features
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Optimization with Sparsity-Inducing Penalties
Foundations and Trends® in Machine Learning
BRIEF: Computing a Local Binary Descriptor Very Fast
IEEE Transactions on Pattern Analysis and Machine Intelligence
ORB: An efficient alternative to SIFT or SURF
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
BRISK: Binary Robust invariant scalable keypoints
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
| Hi-index | 0.00 |
Binary descriptors of image patches are increasingly popular given that they require less storage and enable faster processing. This, however, comes at a price of lower recognition performances. To boost these performances, we project the image patches to a more discriminative subspace, and threshold their coordinates to build our binary descriptor. However, applying complex projections to the patches is slow, which negates some of the advantages of binary descriptors. Hence, our key idea is to learn the discriminative projections so that they can be decomposed into a small number of simple filters for which the responses can be computed fast. We show that with as few as 32 bits per descriptor we outperform the state-of-the-art binary descriptors in terms of both accuracy and efficiency.