Authors
Manju
Abstract
Currently, the world is moving towards digitalization extensively with which crime or forgery related to digital documents, images, and autographs also are growing with plenty of intelligence. Because of the vacuity of advanced result digital cameras, hi-tech and sophisticated personal computers, and powerful software and hardware tools within the image editing and manipulating field, it becomes conceivable for anyone to produce, alter, and modify the contents of a digital image and to violate its legitimacy. Fake and duplicate images are numerous times used to gain popularity in social media and journals. Numerous cases are noted regarding the defaming of businesses similar to political leaders by exploiting fake photos and videos. Digital image forensics aims at confirming the genuineness of images by sicking information about their past. Two important questions are addressed: The first one is the identification of the imaging device that captured that image, and the second one is, therefore, the identification of traces of forgeries. In this review paper, the author reviews the various image forgery detection techniques along with their results. Keywords: Digitalization, Video forgery, digital forensic, forgery, traces of forgery, DWT and SIFT optical flow, etc.
Introduction
In today's digital landscape, images serve as potent communicative tools across various sectors, from journalism to medicine. However, the widespread use of digital imagery has opened the door to image forgery (Sharma, 1990) facilitated by advanced editing software and high-resolution cameras. This presents a pressing challenge to image authenticity and security. Digital forensics (Sharma, 2017) has emerged as a crucial field, offering techniques to authenticate images and detect manipulation. As technology evolves, ensuring the legitimacy of digital images becomes paramount. In response, researchers are continuously developing innovative methods to safeguard image integrity. Despite the convenience and versatility of digital imagery, the threat of forgery underscores the importance of robust security measures and vigilant verification processes. Addressing these challenges is essential to maintaining trust and reliability in the digital realm.
Images are electronic representations of visual information in the form of pixels. Digital images are composed of pixels, tiny squares containing colour and brightness information. They are created by digital cameras, scanners, or software programs. Image files come in formats like JPEG, PNG, GIF, TIFF, and BMP, each with different compression, quality, and compatibility characteristics (Sharma, 1990).
Digital forensics, also known as computer forensics, is the practice of collecting, analysing, and preserving electronic data to be used as evidence in criminal or civil investigations. It involves the use of specialized techniques and tools to extract data from digital devices, such as computers, smartphones, and other digital storage media (Sharma, 2017).
The process typically comprises numerous steps, including:
1. Identification and seizure of digital devices: Investigators must identify all relevant digital devices that may contain relevant data, and then seize them in a manner that preserves the integrity of the data.
2. Preservation of evidence: Investigators must ensure that the data on the seized devices is not altered or destroyed in any way during the investigation.
3. Analysis of data: Investigators must analyse the data on the seized devices to determine their relevance to the investigation and to extract any potential evidence.
4. Presentation of findings: Investigators must present their findings clearly and concisely so that are admissible in court.
Digital image forgery, also known as image manipulation, is the process of altering a digital image to create a new, falsified image and deceiving the viewer into believing that the image is authentic. This can involve adding, removing, or modifying elements within the image, and is typically done to deceive or mislead viewers. Image forgery suggests the manipulation of the digital image to hide some meaningful or helpful information about an image. There are numerous cases when it is tough to recognize the edited region from the original image. The identification of forged images is determined by the need for legitimacy and to preserve the integrity of the image.
The methods used to recognize the forensic changes made are acknowledged as forgery detection (FD) techniques. Image forgery detection techniques include analysing metadata, examining lighting/shadow inconsistencies, and using software tools to detect anomalies in pixel data. A study suggests identifying statistical artefacts in pixel value histograms as intrinsic fingerprints of forgery. Models of original and forged image histograms are compared to detect diagnostic features of pixel value mapping. Various methods in image forensics focus on recognizing tampered images, leveraging developments in the field. Recent developments in image forensics have given upliftment to numerous methods for the recognition of tampered images. Here are some Image forgery detection techniques.
References
Ardizzone, E., A. Bruno, et al. "Copy-Move Forgery Detection via Texture Description." ACM Workshop on Multimedia in Forensics, Security, and Intelligence, vol. 17, Oct 2010, pp. 59-64.
Cao, Gang, et al. “Edge-based Blur Metric for Tamper Detection.” J. Inf. Hiding Multim. Signal Process., vol. 1, Jan. 2010, pp. 20–27.
Chamlawi, Rafiullah, et al. “Authentication and Recovery of Images Using Multiple Watermarks.” Computers & Electrical Engineering, vol. 36, no. 3, Jan. 2010, pp. 578–84.
Christlein, Vincent, et al. “An Evaluation of Popular Copy-Move Forgery Detection Approaches.” IEEE Transactions on Information Forensics and Security, vol. 7, no. 6, Sept. 2012, pp. 1841–54.
Farid, H. "A Survey of Image Forgery Detection." IEEE Signal Processing Magazine, 2006.
Fu, D., Y. Shi, and W. Su. "Detection of Image Splicing Based on Hilbert Huang Transform and Moments of Characteristic Functions with Wavelet Decomposition." International Workshop on Digital Watermarking, 2006.
Gopi, E., N. Lakshmanan, et al. "Digital Image Forgery Detection Using Artificial Neural Network and Autoregressive Coefficients." Canadian Conference on Electrical and Computer Engineering, 2006.
Ibrahim, R.W., Z. Moghaddasi, et al. Noor. "Fractional Differential Texture Descriptors Based on the Machado Entropy for Image Splicing Detection." International Journal of Computer Science Issues, 2015.
Katzenbeisser, S., and F.A. Petitcolas, editors. Information Hiding Techniques for Steganography and Digital Watermarking. Artech House, 2000.
Katzenbeisser, Stephan, and Fabien Petitolas. “Information Hiding Techniques for Steganography and Digital Watermaking.” EDPACS, vol. 28, no. 6, Dec. 2000.
Lin, C.Y., and S.F. Chang. "Generating Robust Digital Signature for Image/Video Authentication." Multimedia and Security Workshop at ACM Multimedia, 1998.
Lu, C.S., and H.Y. Mark Liao. "Structural Digital Signature for Image Authentication: An Incidental Distortion Resistant Scheme." IEEE Transactions on Multimedia, 2003.
Lu, W., W. S. un, and J.W. Huang. "Digital Image Forensics Using Statistical Features and Neural Network Classifiers." International Conference on Machine Learning and Cybernetics, 2008.
Luo, W., Z. Qu, F. Pan, and J. Huang. "A Survey of Passive Technology for Digital Image Forensics." Frontiers of Computer Science in China, 2007.
Mahdian, B., and S. Saic. "Using Noise Inconsistencies for Blind Image Forensics." Image and Vision Computing, 2009.
Makandar, Aziz, and Bhagirathi Halalli. “Image Enhancement Techniques Using Highpass and Lowpass Filters.” International Journal of Computer Applications, vol. 109, no. 14, 16 Jan. 2015.
Moghaddasi, Z., H. A. Jalab, R. Noor, et al. "Improving RLRN Image Splicing Detection with the Use of PCA and Kernel PCA." The Scientific World Journal, 2014.
Munirah, M.Y., N. M. Nawi, et al. "A Comparative Analysis of Feature Selection Techniques for Classification Problems." ARPN Journal of Engineering and Applied Sciences, 2016.
Ng, T.T., S.F. Chang, C.Y. Lin, and Q. Sun. "Passive-Blind Image Forensics." Multimedia Security Technology for Digital Rights, 2006.
Peng, F., Y. Nie, and M. Long. "A Complete Passive Blind Image Copy-Move Forensics Scheme Based on Compound Statistics Features." International Journal of Forensic Science, 2011.
Phkan, A., and M. Borah. "A Survey Paper on the Feature Extraction Module of Offline Handwriting Character Recognition." International Journal of Computer Engineering and Applications, 2014.
Rosales, L., M. Cedillo, et al. "Watermarking Based Image Authentication with Recovery Capability Using Halftoning Technique." Signal Processing: Image Communication, 2013.
Rosales-Roldan, Luis, et al. “Watermarking-based Image Authentication with Recovery Capability Using Halftoning Technique.” Signal Processing. Image Communication, vol. 28, no. 1, Jan. 2013.
Shieh, J.M., D.C. Lou, and T. Ming Chang. "A Semi-Blind Digital Watermarking Scheme Based on Singular Value Decomposition." Computer Standards and Interfaces, 2006.
Soloria, B., and A.K. Nandi. "Automated Detection and Localization of Duplicated Regions Affected by Reflection, Rotation and Scaling in Image Forensics." International Journal of Signal Processing, 2011.
Sutthiwan, P., Y. Q. Shi, et al. "Rake Transform and Edge Statistics for Image Forgery Detection." IEEE International Conference on Multimedia, 2010.
Zhao, Y.Q., M. Liao, et al. "Tampered Region Detection of Imprinting JPEG Images." International Journal on Light and Electron Optics, 2013.
Zhao, Y.Q., N. R. Cao, and G. Ni. "Detection of Image Sharpening Based on Histogram Aberration and Ringing Artifacts." IEEE International Conference on Multimedia and Expo (ICME), 2009.
How to cite this article?
| APA Style | Manju. (2024). Digital Image Forgeries and their Detection Techniques – A Review. Academic Journal of Forensic Sciences, 07(01), 29–37. |
| Chicago Style | |
| MLA Style | |
| DOI | |
| URL |