Fine-search for image copy detection based on local affine-invariant descriptor and spatial dependent matching

Authors:
Hefei Ling;Liyun Wang;Fuhao Zou;Weiqi Yan
Affiliations:
College of Computer Science, Huazhong University of Science & Technology, Wuhan, China;College of Computer Science, Huazhong University of Science & Technology, Wuhan, China;College of Computer Science, Huazhong University of Science & Technology, Wuhan, China;Institute of ECIT, Queen's University Belfast, Belfast, UK BT7 1NN
Venue:
Multimedia Tools and Applications
Year:
2011

Citing 20
Cited 0

Ordinal Measures for Image Correspondence

IEEE Transactions on Pattern Analysis and Machine Intelligence
Duplicate detection in consumer photography and news video

Proceedings of the tenth ACM international conference on Multimedia
Invariant Object Recognition with Discriminant Features Based on Local Fast-Fourier Mellin Transform

ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
Video Google: A Text Retrieval Approach to Object Matching in Videos

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Robust content-based image searches for copyright protection

MMDB '03 Proceedings of the 1st ACM international workshop on Multimedia databases
Scale & Affine Invariant Interest Point Detectors

International Journal of Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Fast and Robust Search Method for Short Video Clips from Large Video Collection

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
An efficient parts-based near-duplicate and sub-image retrieval system

Proceedings of the 12th annual ACM international conference on Multimedia
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
Effective and efficient object-based image retrieval using visual phrases

MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Robust voting algorithm based on labels of behavior for video copy detection

MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Novel image copy detection with rotating tolerance

Journal of Systems and Software
Pruning SIFT for scalable near-duplicate image matching

ADC '07 Proceedings of the eighteenth conference on Australasian database - Volume 63
New local descriptors based on dissociated dipoles

Proceedings of the 6th ACM international conference on Image and video retrieval
Invariant Content-Based Image Retrieval Using a Complete Set of Fourier-Mellin Descriptors

ICMCS '99 Proceedings of the 1999 IEEE International Conference on Multimedia Computing and Systems - Volume 02
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
Content-Based Copy Retrieval Using Distortion-Based Probabilistic Similarity Search

IEEE Transactions on Multimedia
A New Approach to Image Copy Detection Based on Extended Feature Sets

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Copies are somehow a subset of near-duplicates, but the approaches extensively employed in near-duplicate retrieval only obtain rough and imprecise query results. Therefore a fine-search scheme is proposed to refine these rough results and attempt to completely detect the real copies accurately. This scheme first employs a local affine-invariant descriptor based on polar-mapping and discrete Fourier transform. Then a spatial dependent matching method is proposed combining nearest neighbor distance ratio with the spatial relationships among the local features. Experimental results demonstrate that the employed descriptor is more robust, distinctive and suitable for copy detection in comparison with the SIFT descriptor. And the spatial dependent matching is able to improve the recall and precision, and lower the false positives and ambiguities.