A Novel Image Signature based on Local Representative Pattern Mining

Copy Detection plays a critical and unique role in copyright infringement detection. This paper proposes a novel method that is able to find copies in large amount of images database efficiently and effectively. By mining the Representative Patterns (PR) about local keypoints, a robust binary image signature is built according to the spatial distribution of these selected patterns. The performance of this method is evaluated on benchmark datasets INRIA Holidays. It only needs 16 bytes that could handle serious image transformations such as 20% cropping. Results shows that only at one fourth (8.9 ms per image) of BRISK feature extracting time and 0.4% of GIST memory usage, our method has a comparable precision and robustness compared with the state-of-art methods of image signature for large-scale copy detection.

[1]  Milind R. Naphade,et al.  Novel scheme for fast and efficent video sequence matching using compact signatures , 1999, Electronic Imaging.

[2]  Tom Drummond,et al.  Robust feature matching in 2.3µs , 2009, 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[3]  Rakesh Mohan,et al.  Video sequence matching , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[4]  G. Klein,et al.  Parallel Tracking and Mapping for Small AR Workspaces , 2007, 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.

[5]  Roland Siegwart,et al.  BRISK: Binary Robust invariant scalable keypoints , 2011, 2011 International Conference on Computer Vision.

[6]  Darius Burschka,et al.  Adaptive and Generic Corner Detection Based on the Accelerated Segment Test , 2010, ECCV.

[7]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[8]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.

[9]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[10]  Pietro Perona,et al.  Indexing in large scale image collections: Scaling properties and benchmark , 2011, 2011 IEEE Workshop on Applications of Computer Vision (WACV).

[11]  Michael Isard,et al.  Object retrieval with large vocabularies and fast spatial matching , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[13]  Cordelia Schmid,et al.  Evaluation of GIST descriptors for web-scale image search , 2009, CIVR '09.