Learning Based Support Vector Machine Research Articles

Integrating SVM classification with SVD watermarking for intelligent video authentication

In law enforcement applications such as surveillance and forensics, video is often presented as evidence. It is therefore of paramount importance to establish the authenticity and reliability of the video data. This paper presents an intelligent video authentication algorithm which integrates learning based Support Vector Machine classification with Singular Value Decomposition watermarking. During video capture and storage, intrinsic local correlation information is extracted from the frames and embedded in the frames at local levels. Tamper detection and classification is performed using the inherent video information and embedded correlation information. The proposed algorithm is independent of the choice of watermark and does not require any key to store. Further, it is robust to global tampering such as frame addition and removal, local attacks such as object alteration and can differentiate between acceptable operations and malicious tampering. Experiments are performed on an extensive database which contains non-tampered videos and videos with several types of tampering. The results show that the proposed algorithm outperforms existing video authentication algorithms.

A plea for confidence intervals and consideration of generalizability in diagnostic studies

Sir, Many thanks for letting us respond to the interesting letter concerning our recent paper. We are grateful for the chance to clarify the points raised, which suggest our conclusions were too optimistic. In our paper (Kloppel et al. , 2008), we used MRI scans from pathologically proven cases of Alzheimer's disease and frontotemporal lobar degeneration (FTLD) to validate trained sets for a machine learning-based support vector machine (SVM) approach to the categorization of structural scans from normal and each other. This rigorous approach substantially limited the number of available subjects, which we made perfectly clear in our article, but which was unavoidable given our novel approach. Frost and colleagues are right to point out that such low numbers result in larger confidence intervals than if we were able to include more scans. This is an object of our further empirical studies—what is the improvement in classification gained using this technique with greater numbers of scans in the trained set? The graph below (Fig. 1 …