Forensic image analysis using inconsistent noise pattern
- PDF / 6,691,928 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 74 Downloads / 242 Views
THEORETICAL ADVANCES
Forensic image analysis using inconsistent noise pattern Ankit Kumar Jaiswal1 · Rajeev Srivastava1 Received: 31 December 2019 / Accepted: 27 October 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract With the advancement of image acquisition devices and social networking services, a huge volume of image data is generated. Using different image and video processing applications, these image data are manipulated, and thus, original images get tampered. These tampered images are the prime source of spreading fake news, defaming the personalities and in some cases (when used as evidence) misleading the law bodies. Hence before relying totally on the image data, the authenticity of the image must be verified. Works of the literature are reported for the verification of the authenticity of an image based on noise inconsistency. However, these works suffer from limitations of confusion between edges and noise, post-processing operation for localization and need of prior knowledge about an image. To handle these limitations, a noise inconsistencybased technique has been presented here to detect and localize a false region in an image. This work consists of three major steps of pre-processing, noise estimation and post-processing. For the experimental purpose two, publicly available datasets are used. The result is discussed in terms of precision, recall, accuracy and f1-score on the pixel level. The result of the presented work is also compared with the recent state-of-the-art techniques. The average accuracy of the proposed work on datasets is 91.70%, which is highest among state-of-the-art techniques. Keywords Digital image forensics · Noise estimation · Post-processing · Detection method · Localization method
1 Introduction Digital image forensics is a branch of forensic science where the authenticity and origin of digital images are assessed. Today, almost everyone has smart devices with a digital camera in it. Millions of photographs are being clicked every day by these cameras. According to Business Insider India [1], more than 1 trillion photographs were taken in 2016 and 85% of them were taken from smartphones. The purposes of these photographs may differ. Photographs used for other than group/family album or hall decoration may be sensitive in some cases, such as photographs used in the courtroom as evidence, pictures clicked by reporters used in news telecast or publication in the magazine. With the advancement of these smart devices, graphic editing tools and applications * Ankit Kumar Jaiswal [email protected] Rajeev Srivastava [email protected] 1
Computing and Vision Lab, Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi, Uttar Pradesh 221005, India
are also easily available in these devices. In this way, editing or manipulation of images gets easier and cheaper using such tools/applications. Only editing of an image is mild processing while manipulation of an image changes the semantic me
Data Loading...
