Photographic composite detection using circles  

作　　者：Shuyi ZHU Xiaochun CAO Handong ZHAO 

机构地区：[1]School of Computer Science and Technology,Tianjin University,Tianjin 300072,China

出　　处：《Frontiers of Computer Science》2012年第6期741-755,共15页中国计算机科学前沿（英文版）

基　　金：Acknowledgements This work was supported by the National Natural Science Foundation of China （Grant No. 60905019）, National High-tech R＆D Program of China （2012AA011503）, Tianjin Key Technologies R＆D program （11ZCKFGX00800）, Tsinghua-Tencent Joint Laboratory for lnternet Innovation Technology, SKL of CG＆CAD, and Strategic and Pilot Project of CAS （XDA06030601）.

摘　　要：In this work, we propose several new methods for detecting photographic composites using circles. In particular, we focus on three kinds of scenes： （1） two coplanar circles with the same radius; （2） a single circle with its discriminable center; （3） a single circle with geometric constraints for camera calibration. For two circles＇ situation, we first estimate the focal length based on the equality of the sizes of two coplanar circles, and then estimate the normal vector of the world circle plane. Inconsistencies in the angles among the normal vectors （Each circle determines a normal vector） are used as evidence of tampering. On the other hand, for the single circle case, we warp the circle to make metric measurement. To demonstrate the effectiveness of the approach, we present results for synthetic and visually plausible composite images.In this work, we propose several new methods for detecting photographic composites using circles. In particular, we focus on three kinds of scenes： （1） two coplanar circles with the same radius; （2） a single circle with its discriminable center; （3） a single circle with geometric constraints for camera calibration. For two circles＇ situation, we first estimate the focal length based on the equality of the sizes of two coplanar circles, and then estimate the normal vector of the world circle plane. Inconsistencies in the angles among the normal vectors （Each circle determines a normal vector） are used as evidence of tampering. On the other hand, for the single circle case, we warp the circle to make metric measurement. To demonstrate the effectiveness of the approach, we present results for synthetic and visually plausible composite images.

关 键 词：digital forensics two circles a single circle geometric constraints 

分 类 号：TB33[一般工业技术—材料科学与工程] TB852.1