Welcome to the InfoSci Platform
Source Camera Identification Issues: Forensic Features Selection and Robustness

Source Camera Identification Issues: Forensic Features Selection and Robustness

Yongjian Hu, Chang-Tsun Li, Changhui Zhou, Xufeng Lin
Copyright: © 2011 |Volume: 3 |Issue: 4 |Pages: 15
ISSN: 1941-6210|EISSN: 1941-6229|EISBN13: 9781613506486|DOI: 10.4018/jdcf.2011100101
Cite Article Cite Article

MLA

Hu, Yongjian, et al. "Source Camera Identification Issues: Forensic Features Selection and Robustness." IJDCF vol.3, no.4 2011: pp.1-15. http://doi.org/10.4018/jdcf.2011100101

APA

Hu, Y., Li, C., Zhou, C., & Lin, X. (2011). Source Camera Identification Issues: Forensic Features Selection and Robustness. International Journal of Digital Crime and Forensics (IJDCF), 3(4), 1-15. http://doi.org/10.4018/jdcf.2011100101

Chicago

Hu, Yongjian, et al. "Source Camera Identification Issues: Forensic Features Selection and Robustness," International Journal of Digital Crime and Forensics (IJDCF) 3, no.4: 1-15. http://doi.org/10.4018/jdcf.2011100101

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Statistical image features play an important role in forensic identification. Current source camera identification schemes select image features mainly based on classification accuracy and computational efficiency. For forensic investigation purposes; however, these selection criteria are not enough. Consider most real-world photos may have undergone common image processing due to various reasons, source camera classifiers must have the capability to deal with those processed photos. In this work, the authors first build a sample camera classifier using a combination of popular image features, and then reveal its deficiency. Based on the experiments, suggestions for the design of robust camera classifiers are given.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.