An Efficient Approach for Identification of Copy- Move Image Forgery using SURF and SIFT based Techniques Shaik Rasool 1 , Uma N. Dulhare 2 , Vasavi Sravanthi Balusa 3 , Deepthi Joshi 4 and Shaziya jabeen 5 1, 3-5 Methodist College of Engineering and Technology, Hyderabad, India Email: shaikrasool@outlook.com, vasavibvs@gmail.com, deepthijayam@gmail.com, shaziyajabeen@gmail.com 2 Muffakham Jah College of Engineering and Technology, Hyderabad, India, Email: prof.umadulhare@gmail.com Abstract—Internet has changed the world of computers and how we use them. Now there is no field left that may not require internet. It has impacted mostly the fields like image processing, machine learning, cyber security, data mining etc. Technological developments today have made the life so comfortable and easy but also put forward a challenge of authentication of digital data generated from various domains. This has become a major concern for security. To address this concern, we are encapsulating facet point juxtaposition, adaptive over dissection for forgery identification in our proposal. We have based our work on Key point and Section based forgery identification techniques. Adaptive non-intersecting, irregular sections are utilized to uncover suspicious sections in the images. Dissection algorithms are used to assist in this process. Facet points are mined by comparing and juxtaposition each section with its facets. Super pixels are used instead of facet points in the proposed forgery section mining system. The neighbouring sections are melded into facet sections to acquire merged sections which have similar color facets. To end the process morphological operations are used over merged sections to obtain forgery section. The outcomes obtained shows that this proposed algorithm can achieve superior and accurate outcomes even in most critical constraints when compared to other existing approaches. Index Terms— Image Processing, Forgery Identification, Image Forgery, Juxtaposition, Digital Images. I. INTRODUCTION Digital image processing in this modern era has become one of the most protruding domains for research in multidisciplinary fields. The core of electromagnetic spectrum and security is constituted by digital image processing. It has become the primary focus of research with huge scope to safeguard privacy and maintain confidentiality. Achieving the desired outcomes in image processing remains a challenging task that needs an apt solution. Digital images are primary source for forensics, deep learning, AI and thrust areas. Using deep learning techniques today, we can fake eminent personalities thus by posing challenge to forensics to detect forgery images. The disparity between forgery and original image has been narrowed done deeply that it’s almost becoming impractical to identify the difference. This drawback is addressed by proposed work [1]. Image forgery has become very common today in social networks. Copy-move forgery is among well-known digital image manipulation practices today that copies portion of the image and is bonded at a different location Grenze ID: 01.GIJET.9.1.703 © Grenze Scientific Society, 2023 Grenze International Journal of Engineering and Technology, Jan Issue