Results showed that use of sensor noise and correlation detection could give close to 100 percent classification accuracy. Further improvements in classification with fewer training images could be achieved by using the improved method for reference-pattern estimation presented in Chen et al. (2007; 2008). Digital images can be obtained through a variety of sources, including digital cameras and scanners. Lukas et al. (2005a, b; 2006a, b) did the pioneering work to develop source-camera identification techniques using the pattern noise of the imaging sensor, and extended this work to detect forgery in digital camera images. A reference pattern was estimated for each camera and was treated as a unique fingerprint of that camera. To identify the source camera of an unknown image, the noise extracted from the image was correlated with the entire reference camera patterns obtained from training images. This paper sought to verify the results presented in Lukas using a different set of cameras. Figures and references