Feature base fusion for splicing forgery detection based on neuro fuzzy

Abstract

Most of image forensics researches have mainly focused on detection of artifacts introduced by a single processing tool. Thus, they have lead in the development of many specialized algorithms looking for one or more particular footprints under distinct settings. Naturally, the performance of such algorithms are not perfect and accordingly the provided output they might be noisy, inaccurate and only partially correct. Furthermore, in practical scenarios, a forged image is often the result of utilizing several tools made available by the image-processing softwares. Therefore, reliable tamper detection requires developing several tools to deal with various tampering scenarios. Fusion of forgery detection tools based on Fuzzy Inference System has been used before for addressing this problem. Adjusting the Membership Functions and defining proper fuzzy rules for getting optimal results are a time consuming processes. This can be accounted as main disadvantage of Fuzzy Inference Systems. In this study, a Neuro Fuzzy Inference System for fusion of forgery detection tools is developed. The Neural Network characteristic of Neuro Fuzzy Inference Systems provide appropriate tool for automatically adjusting Membership Functions. Moreover, initial Fuzzy inference system is generated based on fuzzy clustering techniques. The purposed framework is implemented and validated on a benchmark image splicing dataset in which three forgery detection tools are fused based on Adaptive Neuro Fuzzy Inference System. The final outcome of the purposed method reveals that applying Neuro Fuzzy Inference systems could be a proper approach for fusion of forgery detection tools. On the best of our knowledge, this is the first time that Neuro Fuzzy Inference Systems employed for fusion of forgery detection tools. Therefore, more researches should be conducted to make it more practical and to increase the effectiveness of methodology.