Improving the Accuracy in Copy-Move Image Detection: A Model of Sharpness and Blurriness

Abstract

The paper suggests a model based on the sharpness and blurriness to confirm the exact tampered areas from the suspicious ones which are detected from similar regions. In copy-move image detection, most research focus on comparing and finding areas with similar properties on the image. Actually, the same areas are not certainly done by copy-move manipulation, they may be the image texture. A model from the sharpness at the collage borderlines and the blurriness inside the image area is built to determine if the areas are really caused by the copy-move manipulation. The combination of feature extraction using oriented FAST and rotated BRIEF (ORB) and tampered region confirmation using a logistic regression model with 98% on accuracy proves the efficiency of the proposed methods.

Effect of Error Level Analysis on The Image Forgery Detection Using Deep Learning

“…The image preprocessing methodology provides 188 two orthogonal vectors to the singular value vector prior to the detection operation, which are critical for detecting fraudulent images. Huynh et al [15] proposes a model based on sharpness and blurriness to distinguish the actual altered locations from suspicious ones discovered in nearby locations. Shelke and Kasana [16] suggested a passive method for detecting and localizing numerous forgeries in video utilizing the Polar Cosine Transform (PCT) and Neighborhood Binary Angular Pattern (NBAP), as well as the GoogleNet model.…”