Augmenting remote multimodal person verification by embedding voice characteristics into face images

This paper presents a biometric watermarking algorithm to augment remote multimodal recognition by embedding voice characteristics into face images. We embed both a fragile watermark for tampering detection, as well as a robust watermark to represent the GMM parameters extracted from voice. We show that the proposed scheme can detect tampering, and is also robust to various watermarking attacks. Person verification experiments on the XM2VTS database indicate the validity of combining face and voice classifiers.