期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2014
期号：ICETS
页码：1545
出版社：S&S Publications
摘要：Digital camera identification can beaccomplished based on sensor pattern noise which isunique to a device and serves as a distinctidentification fingerprint. Camera identification andauthentication has formed the basis of image / videoforensics in legal proceedings. Unfortunately, realtimevideo source identification is a computationallyheavy task, and does not scale well to conventionalsoftware implementations on typical embeddeddevices. In this paper, we propose a hardwarearchitecture for source identification in networkedcameras. The underlying algorithms, an orthogonalforward and inverse Discrete Wavelet Transform(DWT) and Minimum Mean Square Error (MMSE)based Estimation have been optimized for 2D framesequences in terms of area and throughputperformance. We exploit parallelism, pipelining andhardware reuse techniques to minimize hardwareresource utilization and increase the achievablethroughput of the design.
