Copy-move forgery detection using SURF feature extraction and SVM supervised learning technique
- PDF / 1,636,381 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 36 Downloads / 207 Views
(0123456789().,-volV)(0123456789().,-volV)
METHODOLOGIES AND APPLICATION
Copy-move forgery detection using SURF feature extraction and SVM supervised learning technique S. Dhivya1 • J. Sangeetha2 • B. Sudhakar1
Ó Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract The goal of computer vision is to identify objects of interest from images. Copy-move forgery is the process of copying one or more parts of an image and moved into another part of an equivalent image. The detection of copy-move images has many limitations in recognition of objects. In this paper, the proposed work uses Speeded Up Robust Feature (SURF) feature extraction, and the specific object is recognized with the help of the support vector machine. When copy-move forgery was performed, some modifications were done to the image. For instance, turning, scaling, darkening, compression, and noise addition are applied to make effective impersonation forgeries. Here, feature matching process uses the image rotate function, which consists of bicubic and crop operations, and calculates the difference using the blend, scale and joint operation. The results show that forged images are extracted from a given set of test images. The test results exhibit that the proposed technique can get noteworthy and impressive results. Keywords Copy-move forgery detection SURF SVM Object recognition Feature matching
1 Introduction Copy move forgery is the easiest form among various types of image forgery detection. It is easy to perform but it is difficult to detect on image. In this type of image forgery some piece of image is replicated inside the same image (Dhivya and Sudhakar 2019). A human personality is progressively weak in visualizing pictures. An image is generously more dominant than an enormous number of words. We acknowledge what we see. Because of the progression in data innovation, advanced pictures are accessible all over. Different devices are available for
Communicated by V. Loia. & S. Dhivya [email protected] J. Sangeetha [email protected] B. Sudhakar [email protected] 1
Department of Electronics and Communication Engineering, Annamalai University, Annamalai Nagar, Tamil Nadu, India
2
Department of Information Technology, School of Computing, Sastra University, Thanjavur, Tamil Nadu, India
handling pictures. Instruments like Photoshop and Corel Draw can perform alterations over photographs, and these progressions cannot be recognized without special tools. Even non-experts having no information about these apparatuses can make changes to an image and make it indistinguishable from the original (Dhivya and Sudhakar 2018). With the methodology of long-range accommodating correspondence relationships on Facebook and Instagram, there has been an enormous development in the volume of picture data delivered in the last decade. Utilization of picture and video handling programs like GNU Gimp and Adobe Photoshop to make doctored pictures and recordings is a significant problem for web organizations like Face
Data Loading...
