Convolutional neural network for smooth filtering detection. Issue 8 (1st August 2018)

• Record Type: Journal Article
• Authors: Yang, Bin; Sun, Xingming; Cao, Enguo; Hu, Weifeng; Chen, Xianyi
• Is Part Of: IET image processing. Volume 12:Issue 8(2018)
• Page Start: 1432
• Page End: 1438
• Publication Date: 2018-08-01
• Subjects: neural nets -- median filters -- Radon transforms -- image representation -- convolution; convolutional neural network -- smooth filtering detection -- tampered objects -- median filtering -- Gaussian filtering -- deep learning technique -- hierarchical representations -- modified CNN architecture -- filter layer -- frequency feature -- residual feature -- Radon transform; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2017.0683
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Smooth filtering is a common post‐operation which is exploited to blur and conceal the traces of tampered objects. Most of the existing forensic methods aim at detecting only one type of filtering process, such as median filtering or Gaussian filtering, which limits their applications. The authors present a new forensic method based on deep learning technique, which utilises a convolutional neural network (CNN) to automatically learn hierarchical representations from the input images. Unlike conventional CNN models, a modified CNN architecture is specifically designed to identify traces left by the manipulation. A filter layer is added into the CNN. The filtering residual in frequency feature of the input image is extracted by this added layer. The output feature is then fed into the next layer of the CNN. Radon transform is applied to increase the distinctiveness of the residual feature. Experimental results on several public datasets show that the proposed CNN‐based model outperforms some state‐of‐the‐art methods.