Investigating Human Factors in Image Forgery Detection

摘要: In today's age of internet and social media, one can find an enormous volume forged images on-line. These have been used in the past to convey falsified information achieve harmful intentions. The spread effect media only makes this problem more severe. While creating has become easier due software advancements, there is no automated algorithm which reliably detect forgery.Image forgery detection be seen as a subset image understanding problem. Human performance still gold-standard for these type problems when compared existing state-of-art algorithms. We conduct subjective evaluation test with aid eye-tracker investigate into human factors associated compare humans also develop uses data from predict difficulty-level image. experimental results presented paper should facilitate development better algorithms future.