Camera Model Identification Based on the Characteristics of CFA and Interpolation Shang Gao 1, Guanshuo Xu 2, Rui-Min Hu 1,*

Slides:



Advertisements
Similar presentations
QR Code Recognition Based On Image Processing
Advertisements

Robust statistical method for background extraction in image segmentation Doug Keen March 29, 2001.
1 Image Authentication by Detecting Traces of Demosaicing June 23, 2008 Andrew C. Gallagher 1,2 Tsuhan Chen 1 Carnegie Mellon University 1 Eastman Kodak.
Detect Digital Image Forgeries Ting-Wei Hsu. History of photo manipulation 1860 the portrait of Lincoln is a composite of Lincoln ’ s head and John Calhoun.
Digital Image Forensics
A Comprehensive Study on Third Order Statistical Features for Image Splicing Detection Xudong Zhao, Shilin Wang, Shenghong Li and Jianhua Li Shanghai Jiao.
ECE643 DIGITAL IMAGE PROCESSING Steganalysis versus Splicing detection Paper by: Yun Q. Shi, Chunhua Chen, Guorong Xuan and Wei Su By: Nehal Patel Siddharth.
{ Fast Disparity Estimation Using Spatio- temporal Correlation of Disparity Field for Multiview Video Coding Wei Zhu, Xiang Tian, Fan Zhou and Yaowu Chen.
Young Deok Chun, Nam Chul Kim, Member, IEEE, and Ick Hoon Jang, Member, IEEE IEEE TRANSACTIONS ON MULTIMEDIA,OCTOBER 2008.
Detecting Digital Image Forgeries Using Sensor Pattern Noise presented by: Lior Paz Jan Lukas, jessica Fridrich and Miroslav Goljan.
Digital Cameras CCD (Monochrome) RGB Color Filter Array.
Adaptive Rao-Blackwellized Particle Filter and It’s Evaluation for Tracking in Surveillance Xinyu Xu and Baoxin Li, Senior Member, IEEE.
Distinguishing Photographic Images and Photorealistic Computer Graphics Using Visual Vocabulary on Local Image Edges Rong Zhang,Rand-Ding Wang, and Tian-Tsong.
SUSAN: structure-preserving noise reduction EE264: Image Processing Final Presentation by Luke Johnson 6/7/2007.
Student: Hsu-Yung Cheng Advisor: Jenq-Neng Hwang, Professor
Imaging Techniques in Digital Cameras Presented by Jinyun Ren Jan
Rotation Forest: A New Classifier Ensemble Method 交通大學 電子所 蕭晴駿 Juan J. Rodríguez and Ludmila I. Kuncheva.
Digital Images The nature and acquisition of a digital image.
Paul Blythe and Jessica Fridrich Secure Digital Camera.
Presented by: Kamakhaya Argulewar Guided by: Prof. Shweta V. Jain
Median Filtering Detection Using Edge Based Prediction Matrix The 10th IWDW, Atlantic City, New Jersey, USA 23~26 October 2011 School of Information Science.
Overview of State-of-the-Art in Digital Image Forensics H. T. SENCAR and N. MEMON Ashwini Chapte 12/5/08 ECE-643 New Jersey Institute of Technology.
Adaptive Regularization of the NL-Means : Application to Image and Video Denoising IEEE TRANSACTION ON IMAGE PROCESSING , VOL , 23 , NO,8 , AUGUST 2014.
Retaliating Anti-forensics of JPEG Image Compression Based On the Noise Level Estimation PROPOSAL SPRING 2015 ADVISOR: Dr. K.R.Rao Presented by, Komandla.
By Meidika Wardana Kristi, NRP  Digital cameras used to take picture of an object requires three sensors to store the red, blue and green color.
EE 7700 Demosaicking Problem in Digital Cameras. Bahadir K. Gunturk2 Multi-Chip Digital Camera Lens Scene Spectral filters Beam- splitters Sensors To.
Frequency-domain Bayer demosaicking
How A Camera Works Image Sensor Shutter Mirror Lens.
Fuzzy Entropy based feature selection for classification of hyperspectral data Mahesh Pal Department of Civil Engineering National Institute of Technology.
Presented by Daniel Khashabi Joint work with Sebastian Nowozin, Jeremy Jancsary, Andrew W. Fitzgibbon and Bruce Lindbloom.
ALIP: Automatic Linguistic Indexing of Pictures Jia Li The Pennsylvania State University.
Image Enhancement [DVT final project]
Handwritten Hindi Numerals Recognition Kritika Singh Akarshan Sarkar Mentor- Prof. Amitabha Mukerjee.
Introduction to Steganalysis Schemes Multimedia Security.
Computer Graphics and Image Processing (CIS-601).
IGARSS 2011, Vancouver, Canada HYPERSPECTRAL UNMIXING USING A NOVEL CONVERSION MODEL Fereidoun A. Mianji, Member, IEEE, Shuang Zhou, Member, IEEE, Ye Zhang,
Exposing Digital Forgeries in Color Filter Array Interpolated Images By Alin C. Popescu and Hany Farid Presenting - Anat Kaspi.
1 Markov random field: A brief introduction (2) Tzu-Cheng Jen Institute of Electronics, NCTU
A NOVEL METHOD FOR COLOR FACE RECOGNITION USING KNN CLASSIFIER
Chittampally Vasanth Raja vasanthexperiments.wordpress.com.
Visual Computing Computer Vision 2 INFO410 & INFO350 S2 2015
Project Topic : Image Differentiation Name : Bo Li Supervisor: Dr. Jimmy Li.
Demosaicking for Multispectral Filter Array (MSFA)
Analysis on CFA Image Compression Methods Sung Hee Park Albert No EE398A Final Project 1.
 Forensics of image re-sampling (such as image resizing) is an important issue,which can be used for tampering detection, steganography, etc.  Most of.
WCPM 1 Chang-Tsun Li Department of Computer Science University of Warwick UK Image Clustering Based on Camera Fingerprints.
Chapter 24: Perception April 20, Introduction Emphasis on vision Feature extraction approach Model-based approach –S stimulus –W world –f,
IMAGE FORGERY DETECTION Submitted by Deepika Dileep Deepika Dileep S7 IT N0:35 N0:35.
Analysis of denoising filters for photo response non uniformity noise extraction in source camera identification Irene Amerini, Roberto Caldelli, Vito.
Date of download: 6/3/2016 Copyright © 2016 SPIE. All rights reserved. A framework for improved pedestrian detection performance through blind image distortion.
RECONSTRUCTION OF MULTI- SPECTRAL IMAGES USING MAP Gaurav.
Trajectory-Based Ball Detection and Tracking with Aid of Homography in Broadcast Tennis Video Xinguo Yu, Nianjuan Jiang, Ee Luang Ang Present by komod.
Zhaoxia Fu, Yan Han Measurement Volume 45, Issue 4, May 2012, Pages 650–655 Reporter: Jing-Siang, Chen.
Automatic Classification for Pathological Prostate Images Based on Fractal Analysis Source: IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 28, NO. 7, JULY.
Heechul Han and Kwanghoon Sohn
Adaptive Block Coding Order for Intra Prediction in HEVC
An Image Database Retrieval Scheme Based Upon Multivariate Analysis and Data Mining Presented by C.C. Chang Dept. of Computer Science and Information.
Der-Chyuan Lou and Jiang-Lung Liu,
Improving the Performance of Fingerprint Classification
Exposing Digital Forgeries Through Chromatic Aberration Micah K
A New Approach to Track Multiple Vehicles With the Combination of Robust Detection and Two Classifiers Weidong Min , Mengdan Fan, Xiaoguang Guo, and Qing.
Exposing Digital Forgeries by Detecting Traces of Resampling Alin C
Deep Learning Hierarchical Representations for Image Steganalysis
How to Digitize the Natural Color
Acquisition and display of a still color image A-Z
A Self-Reference Watermarking Scheme Based on Wet Paper Coding
Demosaicking Problem in Digital Cameras
Detecting Digital Forgeries using Blind Noise Estimation
Random Neural Network Texture Model
A Quadratic-Residue-based Fragile Watermarking Scheme
Presentation transcript:

Camera Model Identification Based on the Characteristics of CFA and Interpolation Shang Gao 1, Guanshuo Xu 2, Rui-Min Hu 1,* 1. Wuhan University, China; 2. New Jersey Institute of Technology, US

Table of Contents Introduction – Camera Model Identification Color filter Array (CFA) and Color Interpolation in Camera Camera Model Detection Artifacts brought by CFA and Interpolation (Idea of feature extraction) Feature Set 1 Feature Set 2 Feature Set 3 Feature Extraction Flow Diagram Experiment Conclusion

Introduction – Camera Model Identification One category of digital image forensics If the image we are interested in are captured by a digital camera, then, what is the make and model of the camera?

CFA and Interpolation in Camera (1/2) Fig.1. CFA and interpolation processing Fig.2. CFA pattern Images from Internet

CFA and Interpolation in Camera (2/2) The process of interpolation is to estimates lack color component by its existing neighbor color components. It can be regarded as a weighted average processing and is similar as low pass filtering [8, 9, 16]. Theoretically, it leads to the fact that interpolated color components are ‘smoother’ than the original part statistically. [8] H. Cao and A. C. Kot: Accurate detection of demosaicing regularity for digital image forensics. IEEE Transactions on Information Forensics and Security 4(4), pp (2009) [9] Matthias Kirchner: Efficient Estimation of CFA Pattern Configuration in Digital Camera Images. Media Forensics and Security II, Proc. SPIE, Vol (2010)Matthias Kirchner [16] A.E Dirik, N. Memon: Image tamper detection based on demosaicing artifacts. In: ICIP(09), Cairo, Egypt Fig.3. bilinear interpolation kernel (Green channel)

Artifacts brought by CFA and Interpolation We use equation proposed in [16] Consideration We use this feature for camera model identification and expand the feature according to different CFA patterns. There are two pixel sets after interpolation: raw and estimated pixel set. The ‘smooth’ effect by interpolation will lead to different variances between these two sets. The statistical difference between raw pixels values and estimated pixel values is hard to observe using pixel values directly, but it could be more obvious by calculating the statistics of noise part. [16] A.E Dirik, N. Memon: Image tamper detection based on demosaicing artifacts. In: ICIP(09), Cairo, Egypt *Noise residual is found by calculating difference between original image and denosed image. *J. Lukas, J. Fridrich, and M. Goljan, "Digital Camera Identification from Sensor Noise," IEEE Transactions on Information Security and Forensics, vol. 1, no. 2, pp , Rudin, L., Osher, S., and Fatemi, E.: Nonlinear total variation based noise removal algorithms, physica D., 60 (1992), (1)

CFA patterns we considered Fig. 4. (a) Bayer Pattern [15]; (b) modified Bayer Pattern [15]; (c) Diagonal Strip Pattern [15]; (d) Vertical Striped Pattern [15]. [15] R. Lukac and K. N. Plataniotis: Color filter arrays: Design and performance analysis. IEEE Transactions on Consumer Electronics, vol. 51, pp. 1260–1267 (2005)

What contributes to the classification ability of this feature? Sensors of different camera models may have different CFA patterns. Interpolation algorithm varies among different camera models. Although some of the CFA patterns are not common in digital cameras, grouping pixels periodically and find the statistical difference could be able to capture artifacts during the whole image processing pipeline.

Camera Model Detection——Feature set 1: Design (1/2) 33 cases are designed CFA types: Bayer, modified Bayer, diagonal strip, vertical striped pattern Color channel: Green, Red and denote raw and estimated noise under the ith possible sample array Total 36 cases, but 4 cases are same situation for our statistics (Green channel under Bayer and modified Bayer pattern), Final 33 cases (2)

Camera Model Detection—— Feature set 2 Inter- color channel interpolation A popular color difference interpolation scheme [19] utilizes inter-channel correlation between colors to do interpolation. If we assume that the full G is available by some interpolation process, R can be recovered by equation (3). It also can be written as equation (4). Feature design The difference of inter-color is ‘smoothed’, to capture these artifacts, feature 2 is designed as equation (5-7) [19] John S. Ho, Oscar C. Au, Jiantao Zhou, and Yuanfang Guo: INTER-CHANNEL DEMOSAICKING TRACES FOR DIGITAL IMAGE FORENSICS. ICME2010 (3)(4) (5)(6)(7)

Camera Model Detection—— Feature set 3 Design For better identical issue, based on the first feature set, we replace the variance statistics by kurtosis statistics and get 33 features as our third feature set. For the 33 possible sample arrays, kurtosis can reflect minor difference of interpolation. Hence, feature set 3 can be calculated as equation (8). (8)

Camera Model Detection—— Feature Extraction Flow Diagram Fig. 5. feature extraction flow diagram

Experiment: Database (1/5) ‘Dresden Image Database’ a public database designed for benchmarking algorithms in the area of digital image forensics. Setting Most under same or similar acquisition procedure, such as at the same scenes, same taken positions, and same up to two motives with tripods in Dresden, and photographed with each camera of one set with systematically varying camera setting (flash, focal length and interchanging lens, if possible) [21]. For source device detection A collection of same or similar scene images taken by different camera, which can be categorized to do manufactory, model, or device detection or etc.

Experiment: Database (2/5) Table.1. Camera model No.modelDevice num/model Image num/model Image resolution Image format 1CanonIxus ×2304JPEG 2CasioEXZ ×2448JPEG 3FujiFirmFinePixJ ×2448JPEG 4NikonCoolPixS ×3264JPEG 5NikonD70s ×2000JPEG 6NikonD ×2592JPEG 7KodakM ×2748JPEG

Experiment: Method (3/5) Image Blocking four 512x512 sub-blocks from center of each JPEG image (no compression after blocking) Feature extraction 69-D features are extracted from each sub-block Model classification 90% of the images are randomly chosen for training the classifier and the rest of them are used for testing (The random choosing is controlled to make sure the sub-blocks in training part and testing part are not from same image). Fig. 6. blocking position

Experiment: Result (4/5) Table.2. camera model detection accuracy CanonIxus CasioEXZ *0.11 FujiFirmFinePixJ NikonCoolPixS * NikonD70s * * NikonD200*** KodakM ***99.87 Average detection rate under 20 times

Experiment: Result (5/5) The average detection accuracy of our proposed method is 99.32%, For 324-D Markov feature [20], the average detection accuracy is 98.78%. Fig. 7. average detection accuracy [20] Guanshuo Xu, Shang Gao, Yun Qing Shi, RuiMin Hu and Wei Su: Camera-model identification using Markovian transition probability matrix. (IWDW09)

Conclusion The artifacts introduced by CFA and interpolation can be considered as differences between models. Three feature sets are designed to catch the artifacts. Combining them together, 69-D features are obtained to do model detection. We use images from seven models of the Dresden image database as our sample resource. The experiment result shows that the detection accuracy of our proposed method works well on seven camera models. The average detection accuracy is 99.32%.

Qestions?