Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
A SIFT Descriptor with Global Context
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
A Performance Evaluation of Local Descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence
CSIFT: A SIFT Descriptor with Color Invariant Characteristics
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Image registration by local histogram matching
Pattern Recognition
Speeded-Up Robust Features (SURF)
Computer Vision and Image Understanding
PCA-SIFT: a more distinctive representation for local image descriptors
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
| Hi-index | 0.00 |
Scale Invariant Feature Transform (SIFT) is a powerful tool in image/object matching and recognition. However, with its local nature, global information of images, such as the histogram, is ignored in its original formulation. Since histogram matching is almost a necessary condition for a pair of matching images, such ignorance can be problematic especially when SIFT is used for matching images/scenes. In this paper we propose a novel method based on making use of both SIFT features and the local intensity histograms on the feature points in order to achieve more robust image matching. And many false matches can be rejected by the proposed method. Experimental results on natural scene matching and image retrieval have showed the efficiency of the proposed approach.