Detecting Double Compressed JPEG Images Using Quantization Properties
Datum konání: 16.10.2009
Přednášející: Babak Mahdian
Odpovědná osoba: Mahdian
In this presentation, we propose a method for detecting double compressed JPEG images. The method is based on double quantization properties and support vector machine classifiers. Detection of double compressed JPEG images is an important task in image forensics. A quantitative measure of the efficiency of the method is proposed as well.