SIFT based video watermarking resistant to temporal scaling |
| |
| Affiliation: | 1. IIIT Guwahati, Guwahati, India;2. IIT Guwahati, Guwahati, India;1. Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of Korea;2. State Key Laboratory of ISN, Xidian University, Xi’an 710071, China;3. Ming Hsieh Department of Electrical Engineering and the Signal and Image Processing Institute, University of Southern California, Los Angeles, CA 90089-2564, USA;1. The Islamia University of Bahawalpur, Department of Computer Science & Information Technology, Pakistan;2. University of Essex, Colchester, United Kingdom;1. Fujian Key Laboratory of Sensing and Computing for Smart City, School of Information Science and Engineering, Xiamen University, Xiamen 361005, China;2. Department of Computer Science, Xiamen University, Xiamen 361005, China;3. Faculty of Science and Technology, University of Macau, Macao;4. Institute of Information Science, Academia Sinica, Taipei 115, Taiwan;1. Ming Chuan University, Department of Electronic Engineering, No. 5, Deming Rd., Taoyuan City 33348, Taiwan;2. National Central University, Department of Communication Engineering, No. 300, Jhongda Rd., Taoyuan City 32001, Taiwan;1. School of Information Science and Engineering, Lanzhou University, Lanzhou, China;2. School of Art and Design, Zhejiang Sci-Tech University, Hangzhou, China |
| |
| Abstract: | In this paper, a blind video watermarking scheme is proposed which can resist temporal scaling such as frame dropping and frame rate adaptation due to scalable compression by exploiting the scale invariance property of the scale invariant feature transform (SIFT). A video scene can also be viewed from side plane where height is the number of rows in a video frame, width is the number of frames in the scene and depth is the number of columns in the frame. In this work, intensity values of selected embedding locations changed such that strong SIFT feature can be generated. SIFT features are extracted from side plane of the video. These newly generated SIFT features are used for watermark signal and are stored in the database for the authentication. A comprehensive set of experiments has been done to demonstrate the efficacy of the proposed scheme over the existing literature against temporal attacks. |
| |
| Keywords: | Watermarking Scale Invariant Feature Transform (SIFT) Feature points Context coherency |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
