This paper presents a novel biometric watermarking algorithm for improving the recognition accuracy and protecting the face and fingerprint images from tampering. Multi-resolution Discrete Wavelet Transform is used for embedding the face image in a finger print image. An intelligent learning algorithm based on õ-Support Vector Machine (SVM) is introduced to enhance the quality of the extracted face image. The performance of the watermarking algorithm is experimentally validated using existing fingerprint and face recognition algorithms. The results show that the extracted fingerprint and faceimages are of high quality. The use of SVMenhances the performance of face recognition by at least 10% even when the watermarked image is subjected to certain geometric and frequency attacks such as scaling, cropping, compression and filtering. © 2005, The Institute of Electronics, Information and Communication Engineers. All rights reserved.