Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Scale-rotation invariant pattern entropy for keypoint-based near-duplicate detection
IEEE Transactions on Image Processing
Spatial coding for large scale partial-duplicate web image search
Proceedings of the international conference on Multimedia
Large scale partially duplicated web image retrieval
Proceedings of the international conference on Multimedia
Reweighted random walks for graph matching
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Content-adaptive reliable robust lossless data embedding
Neurocomputing
Lossless Data Embedding Using Generalized Statistical Quantity Histogram
IEEE Transactions on Circuits and Systems for Video Technology
Presenting diverse location views with real-time near-duplicate photo elimination
ICDE '13 Proceedings of the 2013 IEEE International Conference on Data Engineering (ICDE 2013)
Hi-index | 0.00 |
In recent years, graph matching has attracted much attention to solve computer vision problems, such as image re-ranking and object recognition. However, graph matching algorithms, e.g., reweighted random walks, cannot be properly applied for near-duplicated image retrieval (NDIR) due to the ignorance of duplicated patches in images. Therefore, this paper proposes a novel graph matching with geometric constraints for NDIR, which explores the spatial relationships in image patches and introduces geometric constraints to remove the false matches, leading to good retrieval results for NDIR. Empirical studies on duplicated ground truth datasets suggest the effectiveness of the proposed approach.