A hybrid model for digital camera source identification

• Published in: 2009 16th IEEE International Conference on Image Processing (ICIP) pp. 2901 - 2904
• Main Authors: Min-Jen Tsai, Cheng-Sheng Wang, Jung Liu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.11.2009
• Subjects: Biosensors; Digital cameras; Digital forensics; Fingerprint recognition; Hardware; Image quality; Image quality metrics; Manufacturing; Photo-response non-uniformity noise; Sensor phenomena and characterization; Support vector machines; Watermarking
• ISBN: 9781424456536; 1424456533
• ISSN: 1522-4880
• DOI: 10.1109/ICIP.2009.5413414

Digital forensics has lately become one of the very important applications to identify the characteristics and the originality of the digital devices. This study has focused on analyzing the relationship between digital cameras and the images. In conjunction with image processing techniques and data exploration methods, it calculates the characteristic values of the images taken by different cameras. Training and categorization are conducted through the support vector machines for identifying the camera source of the images. Based on the fact that the internal imaging algorithms of a camera are different from one manufacturer to another, this method computes the hidden characteristics of the images. The result of experiments shows the proposed approach can obtains 94.95% identification rate when images are taken from 20 different cameras.