Efficient Near-duplicate Detection and Sub-image Retrieval

By Yan Ke, Rahul Sukthankar, Larry Huston. 2004

417 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Product Quantization for Nearest Neighbor Search (2011, methodology): “In this case, one of the most popular ANN algorithms is the Euclidean Locality-Sensitive Hashing (E2LSH) [7], [11], which provides theoretical guarantees on the search quality This work was partly realized as part of the Quaero Programme, funded by OSEO, French State agency for innovation.”
VisualRank: Applying PageRank to Large-Scale Image Search (2008, methodology): “[33] have explored LSH in the task of near-duplicate image detection and retrieval and obtained promising results.”
Effective and Efficient Global Context Verification for Image Copy Detection (2017, background): “typically found between the similar images [20].”
Searching with expectations (2010, methodology): “It has been successfully used for local descriptors [7] and 3D object indexing [12, 9].”
Searching with quantization: approximate nearest neighbor search using short codes and distance estimators (2009, methodology): “It has been successfully used for local descriptors [10] and 3D object indexing [11, 9].”
Semantic manifold learning for image retrieval (2005, background): “, [8, 14, 15, 17], SIFT descriptors are quite effective in representing local image properties.”
The Inverted Multi-Index (2012, methodology): “We also apply the inverted multi-index to the problem of large-scale duplicate detection [36], [37], [38].”
Near Duplicate Image Detection: min-Hash and tf-idf Weighting (2008, methodology): “[12] demonstrate near-duplicate detection and sub-image retrieval by using sparse features, taken from each image, coupled with a disk-based Locality Sensitive Hashing (LSH) for fast approximate search on the individual feature descriptors.”
Locality sensitive hashing: A comparison of hash function types and querying mechanisms (2010, positive): “LSH has been successfully used in several multimedia applications (Ke et al., 2004; Shakhnarovich et al., 2006; Matei et al., 2006).”
Image retrieval: Ideas, influences, and trends of the new age (2008, positive): “Interest point detectors for generating localized image descriptors robust to such changes have been used for near-duplicate detection in [Ke et al. 2004].”