U.S. flag

An official website of the United States government, Department of Justice.

Feature based RDWT watermarking for multimodal biometric system

NCJ Number
305873
Journal
Image and Vision Computing Volume: 27 Issue: 3 Dated: 2009 Pages: 293-304
Date Published
2009
Length
12 pages
Annotation

This paper presents a three-level RDWT biometric watermarking algorithm to embed the voice biometric MFC coefficients in a color face image of the same individual for increased robustness, security, and accuracy.

Abstract

The phase congruency model is used to compute the embedding locations, which preserves the facial features from being watermarked and ensures that the face recognition accuracy is not compromised. The proposed watermarking algorithm uses adaptive user-specific watermarking parameters for improved performance. Using face, voice, and multimodal recognition algorithms, and statistical evaluation, the authors show that the proposed RDWT watermarking algorithm is robust to different frequency and geometric attacks and provides the multimodal biometric verification accuracy of 94%. (Published Abstract Provided)

Date Published: January 1, 2009