A Hybrid Feature Model for Seam Carving Detection

Seam carving, as a content-aware image resizing algorithm, is widely used nowadays. In this paper, an advanced hybrid feature model is presented to reveal the trace of seam carving, especially seam carving at a low carving rate, applied to uncompressed digital images. Two groups of features are designed to capture energy variation and pixel variation caused by seam carving, respectively. As indicated by the experimental works, the state-of-the-art performance on detecting 5% and 10% carving rate cases has been improved from 81.13% and 90.26% to 85.75% and 94.87%, respectively.

[1]  Xingming Sun,et al.  Detecting seam carving based image resizing using local binary patterns , 2015, Comput. Secur..

[2]  Qingzhong Liu,et al.  An approach to detecting JPEG down-recompression and seam carving forgery under recompression anti-forensics , 2017, Pattern Recognit..

[3]  Timothy K. Shih,et al.  Tamper Detection of JPEG Image Due to Seam Modifications , 2015, IEEE Transactions on Information Forensics and Security.

[4]  Gerald Schaefer,et al.  UCID: an uncompressed color image database , 2003, IS&T/SPIE Electronic Imaging.

[5]  Anindya Sarkar,et al.  Detection of seam carving and localization of seam insertions in digital images , 2009, MM&Sec '09.

[6]  Yu-Ju Lin,et al.  A patch analysis method to detect seam carved images , 2014, Pattern Recognit. Lett..

[7]  Ariel Shamir,et al.  Seam Carving for Content-Aware Image Resizing , 2007, ACM Trans. Graph..

[8]  Baochang Zhang,et al.  Local Derivative Pattern Versus Local Binary Pattern: Face Recognition With High-Order Local Pattern Descriptor , 2010, IEEE Transactions on Image Processing.

[9]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Min Wu,et al.  Seam carving estimation using forensic hash , 2011, MM&Sec '11.

[11]  Timothy K. Shih,et al.  Detection of seam carving in JPEG images , 2013, 2013 International Joint Conference on Awareness Science and Technology & Ubi-Media Computing (iCAST 2013 & UMEDIA 2013).

[12]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[13]  Qingzhong Liu,et al.  Improved Approaches with Calibrated Neighboring Joint Density to Steganalysis and Seam-Carved Forgery Detection in JPEG Images , 2014, ACM Trans. Intell. Syst. Technol..

[14]  Yun Q. Shi,et al.  An effective method to detect seam carving , 2017, J. Inf. Secur. Appl..

[15]  Qingzhong Liu.  Exposing seam carving forgery under recompression attacks by hybrid large feature mining , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[16]  A. Piva.  An Overview on Image Forensics , 2013 .

[17]  Gaurav Sharma,et al.  Detecting content adaptive scaling of images for forensic applications , 2010, Electronic Imaging.

[18]  Heung-Kyu Lee,et al.  Detecting Trace of Seam Carving for Forensic Analysis , 2014, IEICE Trans. Inf. Syst..

[19]  Yun Q. Shi,et al.  A Local Derivative Pattern Based Image Forensic Framework for Seam Carving Detection , 2016, IWDW.