In this paper, we propose novel algorithmic models based on feature transformation in cross-modal subspace and their multimodal fusion for different types of residue features extracted from several intra-frame and interframe pixel sub-blocks in video sequences for detecting digital video tampering or forgery. An evaluation of proposed residue features - the noise residue features and the quantization features, their transformation in cross-modal subspace, and their multimodal fusion, for emulated copy-move tamper scenario shows a significant improvement in tamper detection accuracy as compared to single mode features without transformation in cross-modal subspace.
|Title of host publication||Proceedings - 2010 4th International Conference on Network and System Security, NSS 2010|
|Number of pages||8|
|Publication status||Published - 1 Sep 2010|
|Event||4th International Conference on Network and System Security, NSS 2010 - Melbourne, VIC, Australia|
Duration: 1 Sep 2010 → 3 Sep 2010
|Conference||4th International Conference on Network and System Security, NSS 2010|
|Period||1/09/10 → 3/09/10|