基于相机溯源的潜在不良视频通话预警

目前主流的不良视频检测大多基于视频内容分析, 属于计算密集型任务, 不利于巨量视频通话流的实时检测。为此, 本文试图从新的视角来阻断潜在不良视频的传播, 即实时视频流相机溯源。和传统检测内容的方法不同, 本文试图通过检测产生不良视频的相机源来阻断潜在不良视频的传播, 即一旦发现某个正在视频通话的手机产生过不良视频, 就发出安全警告进行阻断。该思路的基本假设是拍摄过不良视频的手机拥有者有更大概率利用同一部手机拍摄不良视频。该思路的核心问题是寻找一种实时、可靠的相机溯源方法。为此, 本文主要聚焦以下三方面工作: 建立了一个包含100部视频的数据库用于算法评估, 数据库中的视频来自25部不同型号、不同品牌的相机, 每一部视频注明了相机来源; 建立了一种简单、有效的视频相机溯源机制, 实现相机的在线实时溯源; 提出了一种多相机指纹特征集成决策模型, 实现可靠的相机溯源。实验结果显示, 所提相机溯源机制能满足相机溯源的实时性要求, 并且所提多相机指纹特征集成决策模型显著优于现有的单一模型, 对于安卓手机, 其视频相机溯源准确率达到98.161%, 验证了该思路的可行性。

Abstract

Majority of the techniques currently employed for detecting illegal videos were primarily based on video content analysis, which in turn was computationally intensive and cannot be applied for real-time detection of large video traffic flow. To address the said issue, the novel approach of real-time video source identification was proposed in this paper for preventing the transmission of illegal videos. In contrast to conventional approached based on content analysis, the proposed approach blocked the transmission of potentially illegal videos by detecting the camera sources that had previously produced illegal videos. If a video call was performed from a cellphone that had previously produced illegal videos, a security warning was issued for blocking the video transmission. The proposed approach was based on the assumption that video streams were more likely to be illegal if they have been produced from a camera that was used earlier for distributing illegal videos. Hence, the primary objective of the proposed approach was to develop a real-time and reliable method for camera source identification. To achieve this two objective, the following three aspects were taken into consideration. Firstly, a database comprising hundred videos was established for evaluation. The videos in the database were obtained from twenty-five cellphones of various brands and models, wherein each video indicated the corresponding camera source. Secondly, a simplified and feasible method was developed for real-time video source identification. Finally, a novel feature decision-making model with multiple integrated fingerprint features was incorporated for enhancing the reliability of video source identification. Obtained experimental results indicate that the proposed approach for camera source identification can meet real-time requirements and is significantly superior to conventional approaches. Furthermore, in the case of Android cellphones, the accuracy of camera source identification is found to be 98.161%, which corroborates the feasibility of the proposed approach.

参考文献

[1] JANA S, PANDE A, CHAN A, et al.. Mobile video chat: issues and challenges ［J］. IEEE Communications Magazine, 2013, 51(6): 144-151.

[2] LUKAS J, FRIDRICH J, GOLJAN M. Digital Camera Identification From Sensor Pattern noise ［J］. IEEE Transactions on Information Forensics and Security, 2006, 1(2): 205-214.

[3] TIAN J, YU W, MA L. Color filter array color reproduction using cycle-spinning ［J］. AEUE-International Journal of Electronics and Communications, 2010, 64(6): 584-587.

[4] GUNTARK B K, GLOZHACH J, ALTUNBASAK Y, et al.. Demosaicking: color filter array interpolation ［J］. IEEE Signal Process Mag, 2005, 22(1): 44-54.

[5] FLECK M M, FORSYTH D A, BREGLER C. Finding naked people ［J］. Inproceedings, 1996: 593-602.

[6] FORSYTH D A, FLECK M M. Body plans［C］. Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 1997: 678..

[7] JONES M J, REHG J M. Statistical Color Models with Application to Skin Detection ［M］. Netherlands: Kluwer Academic Publishers, 2002.

[8] FORSYTH D A, FLECK M M. Automatic detection of human nudes ［J］. International Journal of Computer Vision, 1999, 32(1): 63-77.

[9] ZHU H Y, HIRATA T, MURAMATSU Y. Patch-based skin color detection and its application to pornography image filtering［C］. International Conference on World Wide Web, WWW 2010, Raleigh, North Carolina, Usa, April. DBLP, 2010: 1227-1228.

[10] LEE J S, KUO Y M, CHUNG P C, et al.. Naked image detection based on adaptive and extensible skin color model ［J］. Pattern Recognition, 2007, 40(8): 2261-2270.

[11] ZAIDAN A A, AHMAD N N, KARIM H A, et al.. On the multi-agent learning neural and Bayesian methods in skin detector and pornography classifier: An automated anti-pornography system ［J］. Neurocomputing, 2014, 131(7): 397-418.

[12] ZAIDAN A A, ABDUL KARIM H, AHMAD N N, et al.. An automated anti-pornography system using a skin detector based on artificial intelligence: a review ［J］. International Journal of Pattern Recognition & Artificial Intelligence, 2013, 27(04): 1350012.

[13] HU W, WU O, CHEN Z, et al..Recognition of pornographic web pages by classifying texts and Images ［J］. IEEE Trans Pattern Anal Mach Intell, 2007, 29(6): 1019-1034.

[14] STOTTINGER J, HANBURY A, LIENSHERGER C, et al.. Skin Paths for Contextual Flagging Adult Videos ［M］. Berlin: Advances in Visual Computing. Springer Berlin Heidelberg, 2009: 303-314.

[15] CAETANO C, AVILA S, GUIMARAES S, et al.. Pornography detection using BossaNova video descriptor ［J］. 22nd European Signal Processing Conference, IEEE, 2014: 1681-1685.

[16] PEREZ M, AVILA S, MOREIRA D, et al..Video pornography detection through deep learning techniques and motion information ［J］. Neurocomputing, 2016, 230(C): 279-293.

[17] CHEN S, PANDE A, ZENG K, et al.. Live video forensics: source identification in lossy wireless networks ［J］. IEEE Transactions on Information Forensics & Security, 2014, 10(1): 28-39.

[18] HAMMAMI M, CHABIR Y, CHEN L. Web Guard: A Web Filtering Engine Combining Textual, Structural, and Visual Content-Based Analysis ［M］. IEEE Educational Activities Department, 2006.

[19] LV Q. Towards large-scale mobile sensing and analytics ［J］ Mobile Sensing: Challenges, Opportunities and Future Directions. UbiComp, 2011.

[20] TIAN L, LI S, AHN J, et al.. Understanding User Behavior at Scale in a Mobile Video Chat Application ［C］. Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, 2013.

[21] XING X, LIANG Y L, CHENG H, et al.. SafeVchat: detecting obscene content and misbehaving users in online video chat services［C］. Computing Research Repository, 2011: 685-694.

[22] LV Q. Detecting Misbehavior in Online Video Chat Services ［M］. IEEE Educational Activities Department, 2013.

[23] XING X, LIANG Y L, HUANG S, et al.. Scalable misbehavior detection in online video chat services ［C］. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2013: 552-560.

[24] CHENG H, LIANG Y L, XING X, et al.. Efficient misbehaving user detection in online video chat services ［C］. Proceedings of the Fifth International Conference on Web Search and Web Data Mining, WSDM, Seattle, WA, USA, 2012: 23-32.

[25] BOSSON A, CAWLEY G C, CHAN Y, et al.. Non-retrieval: Blocking Pornographic Images ［C］. International Conference on Image and Video Retrieval. Springer-Verlag, 2002: 50-60.

[26] KHARRAZI M, SENCAR H T, MEMON N. Blind source camera identification ［C］. International Conference on Image Processing. IEEE, 2004(1): 709-712.

[27] GERADTS Z J, KUROSAWA K, KUROKI K. Methods for identification of images acquired with digital cameras ［C］. Enabling Technologies for Law Enforcement and Security. Enabling Technologies for Law Enforcement and Security, 2001: 505-512.

[28] KUROSAWA K, KUROKI K, SAITOH N. CCD fingerprint method-identification of a video camera from videotaped images ［C］. International Conference on Image Processing, 1999. ICIP 99. Proceedings. IEEE, 2002(3): 537-540.

[29] LYU S, FARID H. Detecting hidden messages using higher-order statistics and support vector machines ［C］. Revised Papers From the, International Workshop on Information Hiding. Springer-Verlag, 2008: 340-354.

[30] CHEN M, FRIDRICH J, GOLJAN M. Digital imaging sensor identification(further study) ［J］. Proc Spie, 2007, 6505(6505).

[31] 张晨, 孙世磊, 石文轩, 等.工业线阵CCD相机系统测试与噪声评估［J］. 光学精密工程, 2016, 34(10): 2532-2539.

ZHANG C, SUN S L, SHI W X, et al.. Linear CCD camera System for industry measurement and its noise evaluation ［J］. Opt. Precision Eng. 2016.34(10): 2532-2539.(in Chinese)

[32] 孙宏海, 何舒文, 吴培, 等. 高动态科学级CMOS相机设计与成像分析［J］. 液晶与显示, 2017, 32(3): 240-248.

SUN H H, HE SH W, W P, et al.. Design and imaging analysis of high dynamics scientific CMOS camera ［J］. Chinese Journal of Liquid Crystals and Displays. 2017, 32(3): 240-248.(in Chinese)

[33] 王晓涛, 王绪安, 康宁. CCD摄像机新型光控技术研究［J］. 红外与激光工程, 2016, 45(1): 120003-0120003.

WANG X T, WANG X A, KANG N. New light-control technology research of CCD camera ［J］.Infrared and Laser Engineering. 2016, 45(1): 120003-0120003.(in Chinese)

[34] 潘卫军, 贺强民, 刘涛, 等. CCD信号自适应采样方法的研究和实现［J］. 红外与激光工程, 2016, 45(5): 283-287.

PAN W J, He Q M, Liu T, et al.. Study and realization of adaptive sampling method for CCD signal ［J］. Infrared and Laser Engineering. 2016, 45(5): 283-287.(in Chinese)

[35] LI C T. Source camera identification using enhanced sensor pattern noise ［J］. IEEE Transactions on Information Forensics & Security, 2010, 5(2): 280-287.(in Chinese)

[36] GOLJAN M, FRIDRICH J, FILLER T. Large scale test of sensor fingerprint camera identification ［C］. Media Forensics and Security. International Society for Optics and Photonics, 2009: 72540I-12.

[37] GOLJAN M, FRIDRICH J, FILLER T. Managing a large database of camera fingerprints ［J］. Proceedings of SPIE-The International Society for Optical Engineering, 2010, 7541(3): 175-178.

[38] BAYRAM S, SENCAR H T, MEMON N. Efficient sensor fingerprint matching through fingerprint binarization ［J］. IEEE Transactions on Information Forensics & Security, 2012, 7(4): 1404-1413.

[39] VALSESIA D, COLUCCIA G, BIANCHI T, et al..Compressed fingerprint matching and camera identification via random projections ［J］. IEEE Transactions on Information Forensics & Security, 2015, 10(7): 1472-1485.

[40] GOLJAN M, CHEN M, COMESANA P, et al.. Effect of compression on sensor-fingerprint based camera identification ［J］. Electronic Imaging, 2016(8): 1-10.

[41] CAOH, KOT A C. Accurate Detection of Demosaicing Regularity for Digital Image Forensics ［M］. IEEE Press, 2009.

[42] BAYRAMS, SENCAR H T, MEMON N. Classification of Digital Camera-Models Based on Demosaicing Artifacts ［M］. Elsevier Science Publishers B. V. 2008.

[43] CHEN M, FRIDRICH J, GOLJAN M, et al.. Source digital camcorder identification using sensor photo response non-uniformity ［C］. Electronic Imaging. International Society for Optics and Photonics, 2007.

[44] HOUTEN W V, GERADTS Z. Source video camera identification for multiply compressed videos originating from YouTube ［J］. Digital Investigation, 2009, 6(1): 48-60.

[45] HYUN D K, CHOI C H, LEE H K. Camcorder Identification for Heavily Compressed Low Resolution Videos ［M］. Computer Science and Convergence. Springer Netherlands, 2012: 695-701.

[46] MARCEL BROUWERS, RAHAF MOUSA. Automatic comparison of Photo Response Non Uniformity(PRNU) on youtube ［J］. System and Network Engineering, 2017.

马晓晨, 韦世奎, 蒋翔, 李晓飞. 基于相机溯源的潜在不良视频通话预警[J]. 光学精密工程, 2018, 26(11): 2785. MA Xiao-chen, WEI Shi-kui, JIANG Xiang, LI Xiao-fei. Early warning of illegal video chats based on camera source identification[J]. Optics and Precision Engineering, 2018, 26(11): 2785.

基于相机溯源的潜在不良视频通话预警

关于本站 Cookie 的使用提示

全站搜索

基于相机溯源的潜在不良视频通话预警

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索