JETIREXPLORE- Search Thousands of research papers



Published in:

Volume 7 Issue 6
June-2020
eISSN: 2349-5162

Unique Identifier

JETIR2006286

Page Number

1980-1985

Share This Article


Title

Copy move forgery detection in digital images using Discrete Cosine Transform and Singular Value Decomposition

ISSN

2349-5162

Cite This Article

"Copy move forgery detection in digital images using Discrete Cosine Transform and Singular Value Decomposition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 6, page no.1980-1985, June-2020, Available :http://www.jetir.org/papers/JETIR2006286.pdf

Abstract

There is a strong demand for robust authentication methods that can discern whether an image is forged or not. In this work, a hybrid approach based on discrete cosine transform and singular value decomposition (SVD) to efficiently detect and localize the copy-move forged region is proposed. In order to reduce the computational complexity of the classification procedure, we propose to arrange image blocks in a descending ordered sorted matrix based on the mean values of intensity of blocks. Further edge detection is applied to find the dominant edge pixels in the image by using horizontally and vertically derived sobel edge filter. For matching process, edge pixel blocks are taken from the sorted matrix and matching is carried out for those edge blocks only which have similar mean values. This reduces computation time of the algorithm as very few edge blocks need to be compared. Pair of blocks within each segment has been compared using singular values of DCT coefficients of the blocks, to find regions that exhibit maximum resemblance. Further morphological operation has been applied for the detected forged edge pixels which results in dilation of region in between these pixels. Re-matching is applied in similar manner to extract the actual forged regions in the image. The experimental results has been evaluated using standard copy move forgery CoMoFoD database and quality metrics i.e. sensitivity, specificity and accuracy show how effectively the method identifies the duplicated region as approx. 99% forged pixels has been truly detected as forged on whole database. Furthermore it also detects multiple copy-move forgery within the image.

Key Words

Copy move forgery, DCT, SVD, CoMoFoD dataset

Cite This Article

"Copy move forgery detection in digital images using Discrete Cosine Transform and Singular Value Decomposition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 6, page no. pp1980-1985, June-2020, Available at : http://www.jetir.org/papers/JETIR2006286.pdf

Publication Details

Published Paper ID: JETIR2006286
Registration ID: 233915
Published In: Volume 7 | Issue 6 | Year June-2020
DOI (Digital Object Identifier):
Page No: 1980-1985
ISSN Number: 2349-5162

Download Paper

Preview Article

Download Paper




Cite This Article

"Copy move forgery detection in digital images using Discrete Cosine Transform and Singular Value Decomposition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 6, page no. pp1980-1985, June-2020, Available at : http://www.jetir.org/papers/JETIR2006286.pdf




Preview This Article


Downlaod

Click here for Article Preview