Copy-move forgery detection using image blobs and BRISK feature
- PDF / 2,138,045 Bytes
- 15 Pages / 439.642 x 666.49 pts Page_size
- 80 Downloads / 197 Views
Copy-move forgery detection using image blobs and BRISK feature Patrick Niyishaka1
· Chakravarthy Bhagvati1
Received: 8 August 2019 / Revised: 5 June 2020 / Accepted: 15 June 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract One of the most frequently used types of digital image forgery is copying one area in the image and pasting it into another area of the same image; this is known as the copymove forgery. To overcome the limitations of the existing Block-based and Keypoint-based copy-move forgery detection methods, in this paper, we present an effective technique for copy-move forgery detection that utilizes the image blobs and keypoints. The proposed method is based on the image blobs and Binary Robust Invariant Scalable Keypoints (BRISK) feature. It involves the following stages: the regions of interest called image blobs and BRISK feature are found in the image being analyzed; BRISK keypoints that are located within the same blob are identified; finally, the matching process is performed between BRISK keypoints that are located in different blobs to find similar keypoints for copy-move regions. The proposed method is implemented and evaluated on the copy-move forgery standard datasets MICC-F8multi, MICC-F220, and CoMoFoD. The experimental results show that the proposed method is effective for geometric transformation, such as scaling and rotation, and shows robustness to post-processing operation, such as noise addition, blurring, and jpeg compression. Keywords BRISK · Blob · CMF · CMFD · DoG · LoG
1 Introduction Image tampering is defined as adding or deleting some important features from the image for malicious purposes [20, 23]. In copy-move forgery (CMF), a part of the image is copied and pasted into another part of the same image [23]. Detection methods for this type of forgery are called Copy-Move Forgery Detection (CMFD) and they are generally categorized into Block-based [5] and Keypoint-based approaches [3, 29]. In a Block-based approach, the image is divided into small overlapping or nonoverlapping blocks. These blocks are almost always rectangular or square in shape. Features Patrick Niyishaka
[email protected] 1
University of Hyderabad, Hyderabad - India
Multimedia Tools and Applications
are extracted from the blocks and compared against each other to find which blocks or features match. The Block-based techniques are effective for forgery under Gaussian noise and jpeg compression. The limitations of Block-based techniques include the difficulty of finding the appropriate size of the block. Small blocks increase the computational cost of matching and also do not give robust features. Large blocks cannot be used to detect small forged areas and tend to detect uniform areas as duplicates [27]. In Keypoint-based approach, feature vectors are computed for high-entropy regions without subdividing the image. Feature vectors are then analysed to identify similarities. Keypoints-based techniques are effective for detecting forgeries under scaling and
Data Loading...
