摘要：Background and Objective: Digital imaging, image forgery and its forensics has become an emerging field for research now days. Digital imaging is used to enhance and restore images to make them more meaningful whereas image forgery produces tampered fake images. Digital forensics is required to examine the questioned images and classify them as authentic or tampered. This study aimed to introduce an image tamper detection method using statistical features extracted from Energy Deviation Measure. Materials and Methods: Energy Deviation Measure is a measure of Energy Deviation in pixel neighbourhood in tampered and recompressed images. It is extracted by measuring the inter pixel intensity difference across and inside the DCT block boundary. Features from Energy Deviation Measure have been used to classify the authentic and tampered images. Support Vector Machine is used for classification. Results: The experimental results have shown that the proposed method performs better with fewer dimensions as compared to other state of art methods. It gives improved accuracy and area under curve while classifying images and it is robust to noise and JPEG compression quality factor. Conclusion: The proposed Energy Deviation Measure captures the essential compression characteristics of an image and hence could be successfully utilized in classifying authentic and tampered images.
