The ‘Northumbria Temporal Image Forensics’ Database: Description and Analysis

This paper introduces a standard digital picture dataset specifically designed for temporal digital image forensics. The database, called Northumbria Temporal Image Forensics (NTIF), consists of natural images with full high resolution of indoor and outdoor scenes. The images are organized in temporal order with regular acquisition timeslots spanned over for 94 weeks using ten digital camera devices. 41,684 images were captured from 10 digital cameras belonged to different models and brands. To this end, the subset of images has been annotated with labels spanning over categories based on the temporal factor of one to two weeks. Constructing such a large-scale temporal image database has been a challenging and enduring process. During the construction of NTIF, ethics were fully considered. The proposed dataset will be freely accessible to benefit all researchers in image forensics from academia and industry. This paper aims to describe the NTIF database and highlight the changes in Sensor Pattern Noise over time. Experiments have been conducted in which the correlations between noise residuals appear to be sensitive to the acquisition time of the respective digital images. The results show a clearly different pattern of correlations when the images are captured in different timeslots as compared to those images acquired within the same timeslots.

[1]  Miroslav Goljan,et al.  Digital Camera Identification from Images - Estimating False Acceptance Probability , 2008, IWDW.

[2]  Alessandro Foi,et al.  Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering , 2007, IEEE Transactions on Image Processing.

[3]  Mo Chen,et al.  Determining Image Origin and Integrity Using Sensor Noise , 2008, IEEE Transactions on Information Forensics and Security.

[4]  Fouad Khelifi,et al.  A novel image filtering approach for sensor fingerprint estimation in source camera identification , 2015, 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[5]  Orhan Bulan,et al.  Device temporal forensics: An information theoretic approach , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[6]  Fouad Khelifi,et al.  Weighted averaging-based sensor pattern noise estimation for source camera identification , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[7]  Rainer Böhme,et al.  The 'Dresden Image Database' for benchmarking digital image forensics , 2010, SAC '10.

[8]  Jiwu Huang,et al.  Enhancing Source Camera Identification Performance With a Camera Reference Phase Sensor Pattern Noise , 2012, IEEE Transactions on Information Forensics and Security.

[9]  Miroslav Goljan,et al.  Digital camera identification from sensor pattern noise , 2006, IEEE Transactions on Information Forensics and Security.

[10]  Fouad Khelifi,et al.  Comparative Analysis of a Deep Convolutional Neural Network for Source Camera Identification , 2019, 2019 IEEE 12th International Conference on Global Security, Safety and Sustainability (ICGS3).

[11]  Kannan Ramchandran,et al.  Low-complexity image denoising based on statistical modeling of wavelet coefficients , 1999, IEEE Signal Processing Letters.

[12]  Jessica J. Fridrich,et al.  Determining approximate age of digital images using sensor defects , 2011, Electronic Imaging.

[13]  Fouad Khelifi,et al.  Image Sharpening for Efficient Source Camera Identification Based on Sensor Pattern Noise Estimation , 2013, 2013 Fourth International Conference on Emerging Security Technologies.

[14]  Fouad Khelifi,et al.  Sensor Pattern Noise Estimation Based on Improved Locally Adaptive DCT Filtering and Weighted Averaging for Source Camera Identification and Verification , 2017, IEEE Transactions on Information Forensics and Security.

[15]  Fouad Khelifi,et al.  On the SPN Estimation in Image Forensics: A Systematic Empirical Evaluation , 2017, IEEE Transactions on Information Forensics and Security.

[16]  Chang-Tsun Li,et al.  PCA-based denoising of Sensor Pattern Noise for source camera identification , 2014, 2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP).