SCCRNet: a framework for source camera identification on digital images

Neural Computing and Applications - Tập 36 - Trang 1167-1179 - 2023
C. S. Sychandran1, R. Shreelekshmi2
1Department of Computer Science and Engineering, College of Engineering Trivandrum, (Affiliated to APJ Abdul Kalam Technological University), Thiruvananthapuram, India
2Department of Computer Applications, College of Engineering Trivandrum, (Affiliated to APJ Abdul Kalam Technological University), Thiruvananthapuram, India

Tóm tắt

Identifying the source of digital images is a critical task in digital image forensics. A novel architecture is proposed using a combination of Convolutional layers and residual blocks to distinguish source cameras. The network architecture comprises convolutional layers, residual blocks, batch normalization layers, a fully connected layer and a softmax layer. Architecture aids in learning and extracting the features for identifying the model and sensor level patterns for source camera identification. Multiple patches are taken from each image to increase the sample space size. The experiments on the MICHE-I dataset show an accuracy of 99.47% for model level source camera identification and 96.03% for sensor level identification. Thus, the proposed method is more accurate than the state-of-the-art methods on the MICHE-1 dataset. The proposed architecture yields comparable results on Dresden and VISION datasets also. Moreover, a technique is also proposed to identify the images of unknown camera models by setting a threshold value for the output prediction score.

Tài liệu tham khảo

Lyu S (2006) Digital image forensics: there is more to a picture than meets the eye San CK, Lam EY, Wong KK (2006) Source camera identification using footprints from lens aberration. In: SPIE, 6069:60690 . https://doi.org/10.1117/12.649775 Çeliktutan O, Sankur B, Avcibas I (2008) Blind identification of source cell-phone model. IEEE Trans Inf For Secur 3(3):553–566. https://doi.org/10.1109/TIFS.2008.926993 Korus P (2017) Digital image integrity-a survey of protection and verification techniques. Digital Signal Process 71:1–26. https://doi.org/10.1016/j.dsp.2017.08.009 Bernacki J (2020) A survey on digital camera identification methods. For Sci Int Digit Investig 34:300983. https://doi.org/10.1016/j.fsidi.2020.300983 Huang Y, Zhang J, Huang H (2015) Camera model identification with unknown models. IEEE Trans Inf For Secur 10(12):2692–2704. https://doi.org/10.1109/TIFS.2015.2474836 Tomioka Y, Ito Y, Kitazawa H (2013) Robust digital camera identification based on pairwise magnitude relations of clustered sensor pattern noise. IEEE Trans Inf For Secur 8(12):1986–1995. https://doi.org/10.1109/TIFS.2013.2284761 Zheng Y, Cao Y, Chang C (2020) A puf-based data-device hash for tampered image detection and source camera identification. IEEE Trans Inf For Secur 15:620–634. https://doi.org/10.1109/TIFS.2019.2926777 Huang Y, Cao L, Zhang J, Pan L, Liu Y (2018) Exploring feature coupling and model coupling for image source identification. IEEE Trans Inf For Secur 13(12):3108–3121. https://doi.org/10.1109/TIFS.2018.2838079 Dirik AE, Sencar HT, Memon N (2008) Digital single lens reflex camera identification from traces of sensor dust. IEEE Trans Inf For Secur 3(3):539–552. https://doi.org/10.1109/TIFS.2008.926987 Chennamma H, Rangarajan L (2010) Source camera identification based on sensor readout noise. Int J Digit Crime For 2(3):28–42. https://doi.org/10.4018/jdcf.2010070103 Lukas J, Fridrich J, Goljan M (2006) Digital camera identification from sensor pattern noise. IEEE Trans Inf For Secur 1(2):205–214. https://doi.org/10.1109/TIFS.2006.873602 Li C-T, Li Y (2011) Color-decoupled photo response non-uniformity for digital image forensics. IEEE Trans Circuits Syst Video Technol 22(2):260–271. https://doi.org/10.1109/TCSVT.2011.2160750 Chen M, Fridrich J, Goljan M, Lukás J (2008) Determining image origin and integrity using sensor noise. IEEE Trans Inf For Secur 3(1):74–90. https://doi.org/10.1109/TIFS.2007.916285 Li C-T (2010) Source camera identification using enhanced sensor pattern noise. IEEE Trans Inf For Secur 5(2):280–287. https://doi.org/10.1109/TIFS.2010.2046268 Wu G, Kang X, Liu KR (2012) A context adaptive predictor of sensor pattern noise for camera source identification. In: 2012 19th IEEE International conference on image processing, 237–240 . https://doi.org/10.1109/ICIP.2012.6466839. IEEE Al-Ani M, Khelifi F (2017) On the spn estimation in image forensics: a systematic empirical evaluation. IEEE Trans Inf For Secur 12(5):1067–1081. https://doi.org/10.1109/TIFS.2016.2640938 Zandi N, Razzazi F (2020) Source camera identification using wlbp descriptor. In: 2020 International conference on machine vision and image processing (MVIP), 1–6 . https://doi.org/10.1109/MVIP49855.2020.9187484. IEEE Jiang X, Wei S, Liu T, Zhao R, Zhao Y, Huang H (2021) Blind image clustering for camera source identification via row-sparsity optimization. IEEE Trans Multimedia 23:2602–2613. https://doi.org/10.1109/TMM.2020.3013449 Huang N, He J, Zhu N, Xuan X, Liu G, Chang C (2018) Identification of the source camera of images based on convolutional neural network. Digit Investig 26:72–80. https://doi.org/10.1016/j.diin.2018.08.001 Gloe T, Böhme R (2010) The dresden image database for benchmarking digital image forensics. J Digit For Pract 3(2–4):150–159. https://doi.org/10.1145/1774088.1774427 Wang B, Yin J, Tan S, Li Y, Li M (2018) Source camera model identification based on convolutional neural networks with local binary patterns coding. Signal Process Image Commun 68:162–168. https://doi.org/10.1016/j.image.2018.08.001 Yang P, Ni R, Zhao Y, Zhao W (2019) Source camera identification based on content-adaptive fusion residual networks. Pattern Recogn Lett 119:195–204. https://doi.org/10.1016/j.patrec.2017.10.016 Baroffio L, Bondi L, Bestagini P, Tubaro S (2016) Camera identification with deep convolutional networks. arXiv preprint arXiv:1603.01068 Tuama A, Comby F, Chaumont M (2016) Camera model identification with the use of deep convolutional neural networks. In: IEEE International workshop on information forensics and security (WIFS), 1–6. https://doi.org/10.1109/WIFS.2016.7823908 Freire-Obregón D, Narducci F, Barra S, Castrillón-Santana M (2019) Deep learning for source camera identification on mobile devices. Pattern Recogn Lett 126:86–91. https://doi.org/10.1016/j.patrec.2018.01.005 Zhang G, Wang B, Wei F, Shi K, Wang Y, Sui X, Zhu M (2021) Source camera identification for re-compressed images: a model perspective based on tri-transfer learning. Comput Secur 100:102076. https://doi.org/10.1016/j.cose.2020.102076 Liu Y, Zou Z, Yang Y, Law N-FB, Bharath AA (2021) Efficient source camera identification with diversity-enhanced patch selection and deep residual prediction. Sensors 21(14):4701. https://doi.org/10.3390/s21144701 Khan S, Bianchi T (2021) Fast image clustering based on compressed camera fingerprints. Signal Process Image Commun 91:116070. https://doi.org/10.1016/j.image.2020.116070 Mandelli S, Cozzolino D, Bestagini P, Verdoliva L, Tubaro S (2020) Cnn-based fast source device identification. IEEE Signal Process Lett 27:1285–1289. https://doi.org/10.1109/LSP.2020.3008855 Fanfani M, Piva A, Colombo C (2022) Prnu registration under scale and rotation transform based on convolutional neural networks. Pattern Recogn 124:108413. https://doi.org/10.1016/j.patcog.2021.108413 Bondi L, Baroffio L, Güera D, Bestagini P, Delp EJ, Tubaro S (2016) First steps toward camera model identification with convolutional neural networks. IEEE Signal Process Lett 24(3):259–263. https://doi.org/10.1109/LSP.2016.2641006 Bennabhaktula GS, Alegre E, Karastoyanova D, Azzopardi G (2022) Camera model identification based on forensic traces extracted from homogeneous patches. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2022.117769 Kang C, Kang S (2020) Camera model identification using a deep network and a reduced edge dataset. Neural Comput Appl 32(17):13139–13146 Rafi AM, Tonmoy TI, Kamal U, Wu Q, Hasan M (2021) Remnet: remnant convolutional neural network for camera model identification. Neural Comput Appl 33(8):3655–3670 Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning. pp 448–456 He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 770–778 . https://doi.org/10.1109/CVPR.2016.90 Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT press, Cambridge Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 .https://doi.org/10.48550/arXiv.1409.1556 Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: ICML Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems. pp 1097–1105 De Marsico M, Nappi M, Riccio D, Wechsler H (2015) Mobile iris challenge evaluation (miche)-i, biometric iris dataset and protocols. Pattern Recogn Lett 57:17–23. https://doi.org/10.1016/j.patrec.2015.02.009 Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 4700–4708 https://doi.org/10.1109/CVPR.2017.243 Shullani D, Fontani M, Iuliani M, Shaya OA (2017) Vision: a video and image dataset for source identification. EURASIP J Inf Secur 1:1–16. https://doi.org/10.1186/s13635-017-0067-2