Application of local invariant symmetry features to detect and localize image copy move forgeries
Introduction
In today's world, images are stored in a digital form which carries vital information and hence the integrity of digital images is very essential. For example, digital images can be used in the day to day life in medical diagnosis, television news, magazines, newspapers, and as legal evidence, etc… These images can be easily accessed and their content can also be tampered with using advanced image editing software. In the past decades, the forgery has been detected using the techniques of image watermarking [1], [2], [3], [4], [5] and digital signatures [6], [7], [8], [9] and these techniques require some external information such as watermark and hash value. On the other hand, the latest research studies focus on detecting the image forgeries without external information [10], [11].
There are many kinds of image forgeries and among them, the “copy move/copy paste/cloning forgery” is a challenging one to detect because this forgery is done by copying a portion of the image and pasting it in another portion of the same image. Moreover, the pasted portion also has similar patterns of the copied portion [12]. This kind of forgery can be done either for the purpose of concealing some information or to raise the number of objects. The same has been pictorially presented in Fig. 1, where, a truck in the first row of column (a) has been concealed by copy pasting the region contained the leaves and is shown in the first row of column (b). Similarly, the second row of column (a) contains only one ball, which has been copied and pasted in the same image in another portion to increase the number of objects and it is shown in the second row of (b). Such kinds of tampering are identified in this work by finding the matches among the extracted novel local symmetry features. As the symmetry features are potentially stable and robust when it is explored at multiple scales and multiple locations, local symmetries also can be relatively descriptive. The numerous work has been previously implemented are based on the SIFT (Scale Invariant Feature Transform) and SURF (Speeded Up Robust Features) features. The main disadvantage of SIFT features is a high computational cost, especially in the process of feature extraction and matching. Even though the SURF features are an efficient one, but it lacks in finding the symmetrical pairs of feature points. So, the proposed scheme proposes a novel scheme to extract such features by computing the local symmetry value; these features are computed by analyzing the differences over the symmetry axes. The proposed scheme is designed an algorithm to detect one than one copy-move forgeries and multiple copies of forgeries in a single attempt.
The major objectives of this research study are, (i) to propose a new local invariant feature to detect the forgery, (ii) to design an algorithm to detect single and multi copy move forgeries in a single attempt and (iii) to evaluate the performance of the proposed scheme. The remaining of the paper is structured as follows: Section 2 states about the previous methods, Section 3 furnishes the proposed scheme, Section 4 discusses the experimental results and finally, Section 5 gives the conclusion of the paper.
Section snippets
Previous methods
The copy-move forgery detection techniques are further classified into a block based and visual feature-based methods. There is a large amount of block-based methods are seen in the literature [13], [14], [15], [16], [17], [18], [19] to detect forgeries, but all are time-consuming. In contrast, the feature based method, efficiently detect the forgeries and have less computational complexity compared to block-based methods. The work in [20] employed g2NN test to detect the forgeries using SIFT
Outline of the proposed scheme
The proposed work aims to detect the copy move forgery by a local symmetry features. First, the features are extracted from the image and then the feature matching is performed to identify the matching points of forged regions. These points may be subjected to many copied and moved regions (i.e. multiple copies of the same region and multiple copy-paste) and it may also contain false matches. In order to resolve this issue, the algorithm of Random Sampling Consensus (RANSAC) is repeatedly
Experimental results and discussions
This section introduces the experimental setup; furnishes the datasets and evaluation measures what are all used in this proposed scheme; presents samples results of the proposed scheme and finally compares and discusses the quantitative results achieved by the proposed scheme.
Conclusion
In this paper, a novel image copy move forgery detection scheme for digital images has been proposed and implemented successfully. In this scheme, a new symmetry-based image features are extracted to detect the forgery and the proposed scheme is modified to detect multiple copy move forgeries also. The MICC-F220, MICC-F600 and CMH datasets were used. 83.64%. 5.45% of TPR and FPR respectively were achieved the detection results in MICC-F220 dataset and 5.80% FPR and 75% TPR in MICC-F600 dataset.
References (45)
- et al.
A chaotic system based fragile watermarking scheme for image tamper detection
AEU-Int J Electron Commun
(2011) - et al.
Image forensic signature for content authenticity analysis
J Vis Commun Image Represent
(2012) - et al.
Authentication through Hough transformation generated signature on G-let D3 domain (AHSG)
Procedia Technol
(2013) - et al.
Passive forensics for copy-move image forgery using a method based on DCT and SVD
Forensic Sci Int
(2013) - et al.
Duplication forgery detection using improved DAISY descriptor
Expert Syst Appl
(2013) - et al.
Passive copy move image forgery detection using undecimated dyadic wavelet transform
Digit Invest
(2012) Image copy-move forgery detection based on polar cosine transform and approximate nearest neighbor searching
Forensic Sci Int
(2013)- et al.
Copy-move forgery detection and localization by means of robust clustering with J-linkage
Signal Process Image Commun
(2013) - et al.
Going deeper into copy-move forgery detection: exploring image telltales via multi-scale analysis and voting processes
J Visual Commun Image Represent
(2015) - et al.
DCT based approach for tampered image detection and recovery using block wise fragile watermarking scheme
Pattern recognition and image analysis
(2013)
Image tamper detection based on edge image and chaotic Arnold map
Indian J Sci Technol
A self-recovery fragile watermarking scheme for image authentication with superior localization
Sci China Ser F
Fragile watermarking scheme based on wavelet edge features
J Electr Eng Technol
Structural digital signature for image authentication: an incidental distortion resistant scheme
IEEE Trans Multimed
Image authentication based on digital signature and semi-fragile watermarking
J Comput Sci Tech
Image forgery detection–A survey
IEEE Signal Process Mag
Image copy-move forgery detecting based on local invariant feature
J Multimed
Detection of copy-move forgery in digital images
Exposing digital forgeries by detecting duplicated image regions
Dual tree complex wavelet transform approach to copy-rotate-move forgery detection
Sci China Inf Sci
Efficient dense-field copy move forgery detection
IEEE Trans Inf Forensics Secur
A sift-based forensic method for copy-move attack detection and transformation recovery
IEEE Trans Inf Forensics Secur
Cited by (28)
A robust detection and localization technique for copy-move forgery in digital images
2023, Journal of King Saud University - Computer and Information SciencesCitation Excerpt :Amerini et al. (2013) consider the first researchers that used the keypoint-based technique by adopting Scale Invariant Feature Transform (SIFT). SIFT is a Linear Scale Space technique, It is used to address the problem of scaling; simultaneously, this algorithm failed to reveal small-sized duplicated regions (Ardizzone et al., 2015) proposed another scheme based on SIFT, the algorithm has lower performance in detecting multi-duplicated regions (W. Zhang et al., 2017) proposed an algorithm by utilizing the Speed Up Robust Feature(SURF) to improve detection in the flat areas by using Contrast Limited Adaptive Histogram Equalization(CLAHE) to increase the contrast between pixels, prepares the source image for the SURF detector to reveal the duplicated regions efficiently (Sadeghi et al., 2017; Bi et al., 2016; Vaishnavi and Subashini, 2019) proposed different algorithms based on keypoint-based techniques. However, the main problem in these algorithms is the lack of key points that lead to failure in forgery detection for small-size images and unable to localize and discriminate the duplicated regions because the detected key points are insufficient.
An efficient approach for forgery detection in digital images using Hilbert–Huang transform
2020, Applied Soft Computing JournalCitation Excerpt :Vaishnavi and Subashini used local symmetry features and algorithm of Random Sampling Consensus (RANSAC). The results achieved 90.2% detection accuracy for MICC-F600 datasets [48]. RANSAC and LBP features have been used by Park et al. and achieved 96.82% detection accuracy for MICC-F220 datasets [49].
Robust and accurate detection of image copy-move forgery using PCET-SVD and histogram of block similarity measures
2020, Journal of Information Security and ApplicationsCitation Excerpt :Many forensic methods for copy-move forgery were presented in the past decades, and they are classified into two classes [2]: keypoint-based and block-based technology. The keypoint-based scenarios proposed in [3–6,27] can detect tampering images with intensive textures. Gong et al. [6] developed a local geometrical color scale-invariant features transform (SIFT) descriptor-based approach for exposing duplicated regions.
Keypoint-Based Copy-Move Area Detection
2024, Lecture Notes in Networks and SystemsEnhanced blind image forgery detection using an accurate deep learning based hybrid DCCAE and ADFC
2024, Multimedia Tools and Applications