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 intraframe and inter-frame 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||14th WSEAS International Conference on Communications|
|Editors||Nikos E. Mastorakis, Mladenov Mladenov, Bojkovic Bojkovic|
|Place of Publication||Greece|
|Publisher||World Scientific and Engineering Academy and Society Press (WSEAS)|
|Number of pages||9|
|Publication status||Published - 2010|
|Event||14th WSEAS International Conference on Communications - Corfu Island, Greece|
Duration: 23 Jul 2010 → 25 Jul 2010
|Conference||14th WSEAS International Conference on Communications|
|Period||23/07/10 → 25/07/10|
Chetty, G. (2010). Blind and passive digital video tamper detection based on multimodal fusion. In N. E. Mastorakis, M. Mladenov, & B. Bojkovic (Eds.), 14th WSEAS International Conference on Communications (pp. 109-117). World Scientific and Engineering Academy and Society Press (WSEAS).