Source camera identification issues: Forensic features selection and robustness

作者：Hu, Yongjian; Li, Chang-Tsun; Zhou, Changhui; Lin, Xufeng

来源：International Journal of Digital Crime and Forensics, 2011, 3(4): 1-15.

DOI：10.4018/jdcf.2011100101

• Camera identifications
• Classification accuracy
• Digital image forensics
• Forensic identification
• Forensic investigation
• Image feature selections
• Robust camera classifiers
• Source camera identifications

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.

• 出版日期2011-10
• 单位华南理工大学