Deep siamese network for limited labels classification in source camera identification
- PDF / 987,128 Bytes
- 26 Pages / 439.642 x 666.49 pts Page_size
- 105 Downloads / 221 Views
Deep siamese network for limited labels classification in source camera identification Venkata Udaya Sameer1
· Ruchira Naskar2
Received: 29 January 2019 / Revised: 19 March 2020 / Accepted: 27 May 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Source Camera Identification is a well-known digital forensic challenge of mapping an image to its authentic source. The current state-of-the-art provides a number of successful and efficient solutions to this problem. However, in almost all such existing techniques, a sufficiently large number of image samples is required for pre-processing, before source identification. Limited labels classification is a realistic scenario for a forensic analyst where s/he has access only to a few labelled training samples, available for source camera identification. In such contexts, where obtaining a vast number of image samples (per camera) is infeasible, correctness of existing source identification schemes, is threatened. In this paper, we address the problem of performing accurate source camera identification, with a limited set of labelled training samples, per camera model. We use a few shot learning technique known as deep siamese network here, and achieve significantly improved classification accuracy than the state–of–the–art. Here, the main principle of operation is to form pairs of samples from the same camera models, as well as from different camera models, to enhance the training space. Subsequently, a deep neural network is used to perform source classification. We perform experiments on traditional camera model identification, as well as intra–make and intra–device source identification. We also show that our proposed methodology under limited labels scenario, is robust to image transformations such as rotation, scaling, compression, and additive noise. Keywords Camera · Classification · Few shot · Limited labels · Siamese · Source camera identification
Venkata Udaya Sameer
[email protected] Ruchira Naskar [email protected] 1
Department of Computer Science and Engineering, National Institute of Technology, Rourkela, 769008, India
2
Department of Information Technology, Indian Institute of Engineering Science and Technology, Shibpur, 711103, India
Multimedia Tools and Applications
1 Introduction Digital Forensics is an indispensable repository of tools and techniques to investigate and provide evidences to cyber crimes that are increasing at an alarming rate in today’s digital age. The main mission of a digital forensic analyst is to provide a legal evidence in a court of law against a digital crime. Digital Image Forensics forms the crux of digital forensics with major focus on crimes involving digital images, such as, identifying illegitimate image manipulations, image source authentication, source camera identification, etc. Source Camera Identification is the problem of identifying the authentic camera, which captured an image under question, in a blind way. It is important for a forensic analyst to iden
Data Loading...
