• Sreeletha S H
• Geethu N Nadh

Digital images have been used in a wide variety of applications such as military, law enforcement, reconnaissance, medical diagnosis and media. With the rapid development of image editing tools, it is easy to produce believable manipulated images. A malicious user may perform contrast enhancement as a retouching manipulation. Also contrast enhancement is used for creating composite image. So it is necessary to detect contrast enhancement manipulation in order to verify the originality and authenticity of the digital images. This contrast enhancement may be applied globally and locally on images. In the proposed system SVM (Support Vector Machine) classifier is used for image tampering region detection. SVM classifiers are used to classify the images as genuine or forged. First, develope a framework for the design of composite image forgery. This framework operates by identifying peak position similarities and gap position similarities from an images gray-scale histogram, then adding a SVM classifier to classify the image original or not. Two algorithms are proposed to detect the contrast enhancement involved manipulations are proposed. First, we focus on the detection of global contrast enhancement applied to the previously JPEG-compressed images, which are widespread in real applications. The histogram peak/gap artifacts are distinguished by identifying the zero-height gap fingerprints. Second, we propose to identify the composite image created by enforcing contrast adjustment on either one or both source regions. The positions of detected blockwise peak/gap bins are clustered for recognizing the contrast enhancement mappings applied to different source regions. The consistency between regional artifacts is checked for discovering the image forgeries and locating the composition boundary. We use this technique to identify image forgery more accurately than the previous methods.

Image forgery, Contrast enhancement, Histogram, Composite image, SVM.

"Tampered Region Detection on Digital Images by Efficient SVM Classifier ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.2, Issue 10, page no.36-42, October-2015, Available :http://www.jetir.org/papers/JETIR1510007.pdf

"Tampered Region Detection on Digital Images by Efficient SVM Classifier ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.2, Issue 10, page no. pp36-42, October-2015, Available at : http://www.jetir.org/papers/JETIR1510007.pdf