Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
A Performance Evaluation of Local Descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence
Scalable Recognition with a Vocabulary Tree
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Detection of multiple deformable objects using PCA-SIFT
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
KPB-SIFT: a compact local feature descriptor
Proceedings of the international conference on Multimedia
BRIEF: binary robust independent elementary features
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Discriminative Learning of Local Image 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
SIFT and SURF Performance Evaluation against Various Image Deformations on Benchmark Dataset
DICTA '11 Proceedings of the 2011 International Conference on Digital Image Computing: Techniques and Applications
Feature set reduction for image matching in large scale environments
Proceedings of the 27th Conference on Image and Vision Computing New Zealand
| Hi-index | 0.00 |
Many image retrieval and object recognition systems rely on high-dimensional feature representation schemes such as SIFT. Because of this high dimensionality these features suffer from the curse of dimensionality and high memory needs. In this paper we evaluate an approach that reduces the size of a SIFT descriptor from 128 bytes to 128 bits. We test its performance in an image retrieval application and its robustness in the presence of various image transformations. We also introduce and evaluate a simpler approach that requires no training but requires 512 bits per descriptor.