Image Splicing Detection With Constrained Convolutional Neural Network

An improved approach of image forgery detection, specifically image splicing detection with Constrained Convolutional Neural Network (CNN) is proposed in this research. Image splicing is a common method in image forgery and is often being misused for bad motives such as false idea propaganda. Nowada...

Full description

Saved in:

Bibliographic Details
Main Author:	Lee, Yang Yang
Format:	Thesis
Language:	English
Published:	2019
Subjects:	T Technology
Online Access:	http://eprints.usm.my/51599/1/Image%20Splicing%20Detection%20With%20Constrained%20Convolutional%20Neural%20Network.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-usm-ep.51599
record_format	uketd_dc
spelling	my-usm-ep.515992022-02-21T08:32:53Z Image Splicing Detection With Constrained Convolutional Neural Network 2019-08-01 Lee, Yang Yang T Technology TK Electrical Engineering. Electronics. Nuclear Engineering An improved approach of image forgery detection, specifically image splicing detection with Constrained Convolutional Neural Network (CNN) is proposed in this research. Image splicing is a common method in image forgery and is often being misused for bad motives such as false idea propaganda. Nowadays there are many related efforts in detecting spliced images, but most of them are either feature-specific or complicated algorithms. Constrained CNN is basically a Deep Learning CNN model with its first layer weights being constrained so that it only extracts splicing manipulation features instead of object features. The constrained layer enables the CNN model to learn the required features directly from ubiquitous image input and then performs classification. In this research, the open source datasets, i.e. CASIA, CASIA 2, CUISDE, NIST, and Carvalho image splicing datasets were used for training and benchmarking the proposed CNN model. With the datasets prepared and assembled, the proposed CNN model will have a series of experiments to test for the various parameters as well as to investigate other non-parametric factors such as the data variation itself. Then its hyperparameters will be tuned for optimization. With the trained and tuned CNN model, a cross-database classification evaluation is carried out. The result shows that the CNN can classify image batch with 96.31% in accuracy and 96.3% in F1-Score, but the scores only apply to CASIA 2 dataset. An optimized CNN is shown to be biased to its own train dataset. Hence it is purposely retrained with a merged balanced dataset. With slight adjustment on the proposed CNN, it is found to be able to generalize the overall performance with the highest accuracy of 94.3% in Carvalho dataset and minimum 75.56% in CASIA dataset. Then the proposed CNN is recasted for block-wise splicing localization operation. It performed well in splicing localization at high accuracy in Carvalho dataset with MCC mark of 0.3582. It is able to discriminate the authentic and splicing border in a wide range of images in the cross-database test. It is shown that CNN with constrained convolution algorithm can be used as a general image splicing detection task. 2019-08 Thesis http://eprints.usm.my/51599/ http://eprints.usm.my/51599/1/Image%20Splicing%20Detection%20With%20Constrained%20Convolutional%20Neural%20Network.pdf application/pdf en public masters Universiti Sains Malaysia Pusat Pengajian Kejuruteraan Elektrik & Elektronik
institution	Universiti Sains Malaysia
collection	USM Institutional Repository
language	English
topic	T Technology T Technology
spellingShingle	T Technology T Technology Lee, Yang Yang Image Splicing Detection With Constrained Convolutional Neural Network
description	An improved approach of image forgery detection, specifically image splicing detection with Constrained Convolutional Neural Network (CNN) is proposed in this research. Image splicing is a common method in image forgery and is often being misused for bad motives such as false idea propaganda. Nowadays there are many related efforts in detecting spliced images, but most of them are either feature-specific or complicated algorithms. Constrained CNN is basically a Deep Learning CNN model with its first layer weights being constrained so that it only extracts splicing manipulation features instead of object features. The constrained layer enables the CNN model to learn the required features directly from ubiquitous image input and then performs classification. In this research, the open source datasets, i.e. CASIA, CASIA 2, CUISDE, NIST, and Carvalho image splicing datasets were used for training and benchmarking the proposed CNN model. With the datasets prepared and assembled, the proposed CNN model will have a series of experiments to test for the various parameters as well as to investigate other non-parametric factors such as the data variation itself. Then its hyperparameters will be tuned for optimization. With the trained and tuned CNN model, a cross-database classification evaluation is carried out. The result shows that the CNN can classify image batch with 96.31% in accuracy and 96.3% in F1-Score, but the scores only apply to CASIA 2 dataset. An optimized CNN is shown to be biased to its own train dataset. Hence it is purposely retrained with a merged balanced dataset. With slight adjustment on the proposed CNN, it is found to be able to generalize the overall performance with the highest accuracy of 94.3% in Carvalho dataset and minimum 75.56% in CASIA dataset. Then the proposed CNN is recasted for block-wise splicing localization operation. It performed well in splicing localization at high accuracy in Carvalho dataset with MCC mark of 0.3582. It is able to discriminate the authentic and splicing border in a wide range of images in the cross-database test. It is shown that CNN with constrained convolution algorithm can be used as a general image splicing detection task.
format	Thesis
qualification_level	Master's degree
author	Lee, Yang Yang
author_facet	Lee, Yang Yang
author_sort	Lee, Yang Yang
title	Image Splicing Detection With Constrained Convolutional Neural Network
title_short	Image Splicing Detection With Constrained Convolutional Neural Network
title_full	Image Splicing Detection With Constrained Convolutional Neural Network
title_fullStr	Image Splicing Detection With Constrained Convolutional Neural Network
title_full_unstemmed	Image Splicing Detection With Constrained Convolutional Neural Network
title_sort	image splicing detection with constrained convolutional neural network
granting_institution	Universiti Sains Malaysia
granting_department	Pusat Pengajian Kejuruteraan Elektrik & Elektronik
publishDate	2019
url	http://eprints.usm.my/51599/1/Image%20Splicing%20Detection%20With%20Constrained%20Convolutional%20Neural%20Network.pdf
_version_	1747822085839781888

Image Splicing Detection With Constrained Convolutional Neural Network

Similar Items