Author(s): Meettu Miriam Anujan
Published in: International Journal of Engineering Research & Technology
License: This work is licensed under a Creative Commons Attribution 4.0 International License.
Volume/Issue: Volume. 5 - Issue. 08 , August - 2016
The means and incentive to create digital image forgeries increased because of the increasing use of digital image, thus feature based source camera identification plays a crucial role in the authentication of digital images. The drawback of the conventional systems is the problem of unknown models. To rectify the disadvantage, camera model identification with unknown model was introduced but the accuracy level was found 28%. To increase the accuracy to an acceptable level, the proposed system was introduced. The new scheme consist of four stages: 1) feature extraction 2) unknown detection 3) unknown expansion 4) classification. In feature extraction, the input image is represented in 10 different formats and from each format 34 features are extracted, thus a total of 340 features are extracted from a single image. Then a KNN based unknown detection and a self training based unknown expansion is done. Finally classification is done using multi-class SVM with quadratic kernel. The experiments were carried out on Dresden image collection which confirms the effectiveness of the proposed system. The accuracy of the proposed system is found to be about 86%
Number of Citations for this article: Data not Available
7 Paper(s) Found related to your topic:
Publish your Ph.D/Master's Thesis Online