Blind copy-move forgery detection using SVD and KS test

Ahmed, Belal; Gulliver, T. Aaron; alZahir, Saif

doi:10.1007/s42452-020-3181-6

Cited by 10 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These categories include block-based, keypoint-based, and deep learning-based approaches. Blockbased approaches involve the extraction of local features by utilizing overlapping or non-overlapping patches [8], whereas key-point-based approaches focus on patches that FIGURE 1: These images depict instances of copy-move manipulation. The initial row exhibits unaltered images, whilst the subsequent row showcases modified images.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The data indicate that our approach consistently detects and precisely determines the location of manipulation, regardless of the degree of post-processing used, ranging from mild (level 1) to severe (level 3). The outcomes of additional post-processing are depicted in Figure (8). The Multiscale Detector detector employs a clustering technique to preserve similarity across key-points, while also effectively capturing local image information using a Multiscale Detector.…”

Section: B Detection Of Manipulated Images With Post-processingmentioning

confidence: 99%

See 1 more Smart Citation

Advancing Copy-Move Manipulation Detection in Complex Image Scenarios Through Multiscale Detector

Diwan,

Mahadeva,

Gupta

2024

IEEE Access

View full text Add to dashboard Cite

This research presents a new approach for identifying instances of copy-move forgeries in digital images by utilizing the Multiscale Detector a Neural Network-based method, which serves as an image key-point detector and descriptor. The act of copy-move manipulation involves the replication and subsequent insertion of a specific segment of an image, intending to modify the overall content of the image. The approach we utilize leverages the sophisticated functionalities of Multiscale Detector, a framework that combines key-point detection with descriptor extraction, to accurately detect and localize instances of copy-move manipulation. The effectiveness of our approach is assessed on a range of copy-move forgeries, encompassing instances that have undergone post-processing and geometric transformations. The experimental findings illustrate the resilience of our approach in identifying instances of manipulations over a diverse range of textured images and various alteration approaches. Furthermore, our approach demonstrates strong performance even when subjected to supplementary processing procedures such as brightness modification, color reduction, contrast adjustment, and blurring. Our suggested method has greater performance when compared to the existing manipulation detection approach, as demonstrated through a comparative analysis. In addition, the algorithm we have developed has high computing efficiency, allowing for real-time detection of forgeries. The methodology employed in this study, which builds upon the Multiscale Detector framework, offers a highly effective approach to the detection of copy-move manipulations in digital images.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: B Detection Of Manipulated Images With Post-processingmentioning

confidence: 99%

Advancing Copy-Move Manipulation Detection in Complex Image Scenarios Through Multiscale Detector

Diwan,

Mahadeva,

Gupta

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The proposed method performed well regarding its recall, precision, and F1 score. For brightness adjustment, it scored at 95%, while for image blurring, it was at 77.5%, 82.7%, and 75% [57].…”

Section: Singular Value Decomposition Algorithm In Digital Forensicsmentioning

confidence: 99%

The Use of Machine Learning in Digital Forensics: Review Paper

Balushi¹,

Shaker²,

Kumar³

2023

Proceedings of the 1st International Conference on Innovation in Information Technology and Business (ICIITB 2022)

View full text Add to dashboard Cite

With the increase of cybercrimes in the current years, digital forensics has become an important matter to study in order achieve quality evidence. Forensic investigators face difficulties with data collection and analysis to reconstruct events. Due to humans' immense interaction on a daily basis, machine learning allows investigators to perform more effective and efficient investigations using various algorithms. Machine learning is a subset of the artificial intelligence field. It is a scientific discipline focusing on developing computer models and algorithms that can perform specific tasks without programming, such as dataset training and testing, and it's potential to aid in investigations. This paper reviews various machine learning techniques that examine and analyze digital evidence during the investigation process. Each machine learning algorithm works on a specific area of digital forensics based on the features, it overcomes complexity, data volume, time-lining, correlation, consistency, etc. moreover, this study compares machine learning algorithms in terms of standard criteria.

show abstract

“…This matrix is applied to the image using an affine transformation which results in the upper part of the image shifted to the right and the lower part shifted to the left. With zoom, two values are randomly chosen from the range [1,10] corresponding to the image width and height. These values are used to create a zoom matrix which is applied to the image using an affine transformation.…”

Section: Data Augmentationmentioning

confidence: 99%

“…Most can be classified as block-based, keypointbased or transform-based methods. In [1], a singular value decomposition (SVD) technique was proposed to extract image features. First the image is partitioned into square blocks and then SVD is applied to each block to obtain the feature vectors.…”

Section: Introductionmentioning

confidence: 99%

Localization and Detection of Copy-Move Forgeries in Post-processed Images Using U-Net

2021

Self Cite

View full text Add to dashboard Cite

Identification and localization of forgeries in images is of great importance in the field of image processing. Many methods have been introduced to solve this problem. Most provide acceptable results on high resolution images but perform poorly when the resolution is low. Images can be post-processed using techniques such as JPEG compression, brightness change, and the addition of noise to improve the visual quality or create copies for various purposes. Therefore, a new deep learning method is introduced to detect forgeries in images even after post-processing. The proposed model is based on an encoderdecoder architecture designed to learn discriminative features across the boundaries of forged regions. A computer-generated dataset is used for training and evaluation is done using the well-known CoMoFoD dataset. The performance is evaluated using six post-processing techniques, namely brightness change, contrast adjustment, color reduction, image blurring, JPEG compression, and noise addition. To train a robust model for these techniques, data augmentation is employed. The results obtained show that the proposed model outperforms seven recent methods in the literature.

show abstract

Blind copy-move forgery detection using SVD and KS test

Cited by 10 publications

References 32 publications

Advancing Copy-Move Manipulation Detection in Complex Image Scenarios Through Multiscale Detector

Advancing Copy-Move Manipulation Detection in Complex Image Scenarios Through Multiscale Detector

The Use of Machine Learning in Digital Forensics: Review Paper

Localization and Detection of Copy-Move Forgeries in Post-processed Images Using U-Net

Contact Info

Product

Resources

About