Athanasiadou Eleni, Geradts Zeno, Van Eijk Erwin
Department of Forensic Science University of Amsterdam, Amsterdam, The Netherlands.
Netherlands Forensic Institute Den Haag, Den Haag, The Netherlands.
Forensic Sci Res. 2018 Oct 17;3(3):210-218. doi: 10.1080/20961790.2018.1485198. eCollection 2018.
In this paper, camera recognition with the use of deep learning technique is introduced. To identify the various cameras, their characteristic photo-response non-uniformity (PRNU) noise pattern was extracted. In forensic science, it is important, especially for child pornography cases, to link a photo or a set of photos to a specific camera. Deep learning is a sub-field of machine learning which trains the computer as a human brain to recognize similarities and differences by scanning it, in order to identify an object. The innovation of this research is the use of PRNU noise patterns and a deep learning technique in order to achieve camera identification. In this paper, AlexNet was modified producing an improved training procedure with high maximum accuracy of 80%-90%. DIGITS showed to have identified correctly six cameras out of 10 with a success rate higher than 75% in the database. However, many of the cameras were falsely identified indicating a fault occurring during the procedure. A possible explanation for this is that the PRNU signal is based on the quality of the sensor and the artefacts introduced during the production process of the camera. Some manufacturers may use the same or similar imaging sensors, which could result in similar PRNU noise patterns. In an attempt to form a database which contained different cameras of the same model as different categories, the accuracy rate was low. This provided further proof of the limitations of this technique, since PRNU is stochastic in nature and should be able to distinguish between different cameras from the same brand. Therefore, this study showed that current convolutional neural networks (CNNs) cannot achieve individualization with PRNU patterns. Nevertheless, the paper provided material for further research.
本文介绍了利用深度学习技术进行相机识别。为识别各种相机，提取了它们独特的光响应非均匀性（PRNU）噪声模式。在法医学中，将一张照片或一组照片与特定相机关联起来非常重要，尤其是在儿童色情案件中。深度学习是机器学习的一个子领域，它将计算机训练成人类大脑，通过扫描来识别异同，以识别物体。本研究的创新之处在于利用PRNU噪声模式和深度学习技术来实现相机识别。本文对AlexNet进行了改进，产生了一种改进的训练程序，最高准确率可达80%-90%。在数据库中，DIGITS显示在10台相机中正确识别出6台，成功率高于75%。然而，许多相机被错误识别，这表明在该过程中出现了故障。对此的一个可能解释是，PRNU信号基于传感器的质量以及相机生产过程中引入的伪像。一些制造商可能使用相同或相似的成像传感器，这可能导致相似的PRNU噪声模式。试图将同一型号的不同相机作为不同类别形成一个数据库时，准确率较低。这进一步证明了该技术的局限性，因为PRNU本质上是随机的，应该能够区分同一品牌的不同相机。因此，本研究表明当前的卷积神经网络（CNN）无法通过PRNU模式实现个体化识别。尽管如此，本文为进一步研究提供了素材。
