Single image camera identification using I-vectors
Arash Rashidi, Farbod Razzazi · 2017
Recently, in the field of speech processing, I-Vector modeling has been appealed a great deal of interest. I-Vector has shown its benefits in modeling of intra and inter-domain variabilities to a single low dimension space for speaker identification tasks. This paper presents the usage of I-Vector in camera identification as a new approach in image forensics domain. In our approach, image texture is extracted from images as our features for the I-vector system. We have used 8 camera models in our work and the result shows 99.01% accuracy. We have also conducted attacks on the test images. We gained 99.01% accuracy for rotation attack and the average accuracy of 88.71% for three level brightness attack.