An efficient model for copy-move image forgery detection

Huynh, Kha-Tu; Ly-Tu, Nga; Le-Tien, Thuong

doi:10.1108/ijwis-04-2022-0088

Cited by 5 publications

(2 citation statements)

References 26 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors benchmarked their work against the literature and proved the efficiency of their proposed method. In the same context, Huynh et al [13] suggested an efficient method for copy-move forgery. They involved classification and clustering techniques.…”

Section: Related Workmentioning

confidence: 99%

Copy-Move Forgery Detection Using Texture Features of Hidden Forged Regions

Saeed¹,

Hamid²,

Hassan³

2023

Technium

View full text Add to dashboard Cite

The recent revolution in technology has not only eased our daily activities at work and home but also introduced new threats. In their daily activities, people exchange a lot of files such as text files, images, videos, etc. that can be used for a variety of purposes. One of the most common types of files is images. These kinds of files can be used to socialize people or spread knowledge among communities. Some of the exchanged images are fake or forged which can lead to the spread of misinformation, which is dangerous. This paper tries to suggest a method for image forgery detection that is copy-move-based. This means a part of the image is used to hide or change other parts in the same image. The suggested method divides an image into several blocks. The feature vectors of the blocks are extracted using a modified Gabor filter. The extracted features are, then, reduced using the principal component analysis technique. The next step is to match the blocks and extract similar ones (duplicated blocks). The findings show that the suggested method is efficient compared to other methods in the literature in terms of detection rate and false positive detection. Also, the proposed method detected forged regions of images when having a 60% of compression rate.

show abstract

Section: Related Workmentioning

confidence: 99%

Copy-Move Forgery Detection Using Texture Features of Hidden Forged Regions

Saeed¹,

Hamid²,

Hassan³

2023

Technium

View full text Add to dashboard Cite

show abstract

“…As a result, efficient algorithms for RSI processing have become a central focus of recent computer vision research (Aljumaily et al , 2023; Guo et al , 2023). A decade ago, these algorithms relied heavily on patterns designed by humans (Huynh et al , 2022; Zheng et al , 2023). However, the advent of deep neural networks and automatic feature extraction methods has led to the dominance of convolutional neural networks (CNNs) in RSI recognition over the past decade (Dimitrovski et al , 2023), likely doubling classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

Efficient knowledge distillation for remote sensing image classification: a CNN-based approach

Song,

Wei,

Yong

2023

IJWIS

View full text Add to dashboard Cite

Purpose The paper aims to tackle the classification of Remote Sensing Images (RSIs), which presents a significant challenge for computer algorithms due to the inherent characteristics of clustered ground objects and noisy backgrounds. Recent research typically leverages larger volume models to achieve advanced performance. However, the operating environments of remote sensing commonly cannot provide unconstrained computational and storage resources. It requires lightweight algorithms with exceptional generalization capabilities. Design/methodology/approach This study introduces an efficient knowledge distillation (KD) method to build a lightweight yet precise convolutional neural network (CNN) classifier. This method also aims to substantially decrease the training time expenses commonly linked with traditional KD techniques. This approach entails extensive alterations to both the model training framework and the distillation process, each tailored to the unique characteristics of RSIs. In particular, this study establishes a robust ensemble teacher by independently training two CNN models using a customized, efficient training algorithm. Following this, this study modifies a KD loss function to mitigate the suppression of non-target category predictions, which are essential for capturing the inter- and intra-similarity of RSIs. Findings This study validated the student model, termed KD-enhanced network (KDE-Net), obtained through the KD process on three benchmark RSI data sets. The KDE-Net surpasses 42 other state-of-the-art methods in the literature published from 2020 to 2023. Compared to the top-ranked method’s performance on the challenging NWPU45 data set, KDE-Net demonstrated a noticeable 0.4% increase in overall accuracy with a significant 88% reduction in parameters. Meanwhile, this study’s reformed KD framework significantly enhances the knowledge transfer speed by at least three times. Originality/value This study illustrates that the logit-based KD technique can effectively develop lightweight CNN classifiers for RSI classification without substantial sacrifices in computation and storage costs. Compared to neural architecture search or other methods aiming to provide lightweight solutions, this study’s KDE-Net, based on the inherent characteristics of RSIs, is currently more efficient in constructing accurate yet lightweight classifiers for RSI classification.

show abstract