DocumentCode :
2278300
Title :
Secure SIFT-based sparse representation for image copy detection and recognition
Author :
Kang, Li-Wei ; Hsu, Chao-Yung ; Chen, Hung-Wei ; Lu, Chun-Shien
Author_Institution :
Inst. of Inf. Sci., Acad. Sinica, Taipei, Taiwan
fYear :
2010
fDate :
19-23 July 2010
Firstpage :
1248
Lastpage :
1253
Abstract :
In this paper, we formulate the problems of image copy detection and image recognition in terms of sparse representation. To achieve robustness, security, and efficient storage of image features, we propose to extract compact local feature descriptors via constructing the basis of the SIFT-based feature vectors extracted from the secure SIFT domain of an image. Image copy detection can be efficiently accomplished based on the sparse representations and reconstruction errors of the features extracted from an image possibly manipulated by signal processing or geometric attacks. For image recognition, we show that the features of a query image can be represented as sparse linear combinations of the features extracted from the training images belonging to the same cluster. Hence, image recognition can also be cast as a sparse representation problem. Then, we formulate our sparse representation problem as an l1-minimization problem. Promising results regarding image copy detection and recognition have been verified, respectively, through the simulations conducted on several content-preserving attacks defined in the Stirmark benchmark and Caltech-101 dataset.
Keywords :
feature extraction; image recognition; image representation; security of data; SIFT-based sparse representation; content-preserving attacks; feature vector extraction; geometric attacks; image copy detection; image copy recognition; l1-minimization; scale invariant feature transform; signal processing attack; Atomic measurements; Dictionaries; Feature extraction; Image recognition; Image reconstruction; Training; Vectors; Sparse representation; compressive sensing; copy detection; image recognition; secure SIFT;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia and Expo (ICME), 2010 IEEE International Conference on
Conference_Location :
Suntec City
ISSN :
1945-7871
Print_ISBN :
978-1-4244-7491-2
Type :
conf
DOI :
10.1109/ICME.2010.5582615
Filename :
5582615
Link To Document :
بازگشت