Hits:

Indexed by:会议论文

Date of Publication:2010-07-12

Included Journals:EI、Scopus

Volume:2

Page Number:590-594

Abstract:This paper proposes a new method for source cellphone identification based on mutli-feature fusion. For a given image which is taken by cell-phone camera, three sets of features are used in this paper, they are higher-order statistics, image quality measures and CFA interpolation coefficients. The feature selection process is implemented with SFFS method to construct a vector of 19 features selected from these 3 sets of features, and the vector is then fed to the SVM classifier. The experiment shows that this algorithm gives an average accuracy of 95.94%, which is better than the existing ones.