Research Area:  Digital Forensics

Abstract:

Photographers are able to create composites of analog pictures, this process is very time consuming and require expert knowledge.In digital image the editing software makes modifications in straight forward.In this project analyze one of the most common form of photographic manipulation known as image composition or splicing.For that propose a forgery detection method is used to exploits subtle inconsistencies in the colour of the illumination of images.The technique ( Machine Learning) is applicable to images containing two or more people. To achieving this concept, the information from physics (chromaticity)- and statistical(texture and edge) - based illuminate estimators on image regions of similar images are taken.Then the extracted texture,skin pigmentation - and edge - based features are provided to a machine - learning approach for automatic decision - making. The classification performance achieved by an SVM (Support Vector Machine) meta - fusion classifier.

Keywords:  

Author(s) Name:  S.L.Jothilakshmi, K Valli, A.Vanitha, A. Selva nathiya, A.Shunmuga priya

Publisher name:  SSRG

DOI:  10.14445/23488360/IJME-V1I1P101

Volume Information:  Volume 1 Issue 1

Paper Link:   https://www.internationaljournalssrg.org/IJME/paper-details?Id=210