Selecting forensic features for robust source camera identification

Yongjian Hu, Chang Tsun Li, Changhui Zhou

Research output: Book chapter/Published conference paperConference paper

13 Citations (Scopus)


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, we first build a sample camera classifier using a combination of popular image features, and then reveal its deficiency. Based on our experiments, suggestions for the design of robust camera classifiers are given.

Original languageEnglish
Title of host publicationICS 2010 - International Computer Symposium
Number of pages6
Publication statusPublished - 2010
Event2010 International Computer Symposium, ICS 2010 - Tainan, Taiwan, Province of China
Duration: 16 Dec 201018 Dec 2010


Conference2010 International Computer Symposium, ICS 2010
CountryTaiwan, Province of China

Fingerprint Dive into the research topics of 'Selecting forensic features for robust source camera identification'. Together they form a unique fingerprint.

  • Cite this

    Hu, Y., Li, C. T., & Zhou, C. (2010). Selecting forensic features for robust source camera identification. In ICS 2010 - International Computer Symposium (pp. 506-511). [5685458]