A Novel Approach of Detecting Image Forgery Using GLCM and KNN

Photos have been utilized to report day-time occasions. They have frequently served as proof in audience chamber, in spite of the fact that picture takers are adequate to form composites of analogy images. This preparation is exceptionally pace expending and desires master information. Nowadays, in...

Full description

Saved in:
Bibliographic Details
Published in2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD) pp. 125 - 129
Main Authors Azam, Kazi Sultana Farhana, Riya, Farhin Farhad, Al Mamun, Shamim, Kaiser, Md.Shamim
Format Conference Proceeding
LanguageEnglish
Published IEEE 27.02.2021
Subjects
Forgery
GLCM
grayscale conversion
image forgery
KNN
Length measurement
MCC-F220 dataset
Media
Security
Sustainable development
Training
Vents
Online AccessGet full text

Cover

More Information
Summary:Photos have been utilized to report day-time occasions. They have frequently served as proof in audience chamber, in spite of the fact that picture takers are adequate to form composites of analogy images. This preparation is exceptionally pace expending and desires master information. Nowadays, in any case, effective computerized picture altering program makes picture adjustments direct. This undercuts our beliefs in photos and in specific investigation of images as prove for real universal vents. There are two sorts of methods for picture forensics: one is dynamic security, and the other is detached discovery. The most sorts of Picture imitation procedures are Picture Spicing; Copy-Move fraud is utilized mainly to examine the tempered photos. As the imitation of pictures proliferates day-by-day, it is indispensable to develop apparatuses for distingue between genuine and tempered images; therefore, we plan to analyze the copy-move imitation. This paper has proposed a combined method of feature collection using GLCM and training with KNN. Our method has given an 85.42% of accuracy level compared with other states of art papers in image forgery detection.
DOI:10.1109/ICICT4SD50815.2021.9397057