Semester
Fall
Date of Graduation
2004
Document Type
Thesis
Degree Type
MS
College
Statler College of Engineering and Mineral Resources
Department
Lane Department of Computer Science and Electrical Engineering
Committee Chair
Afzel Noore.
Abstract
This research presents contextual digital watermarking techniques using face and demographic text data as multiple watermarks for protecting the evidentiary integrity of fingerprint image. The proposed techniques embed the watermarks into selected regions of fingerprint image in MDCT and DWT domains. A general image watermarking algorithm is developed to investigate the application of MDCT in the elimination of blocking artifacts. The application of MDCT has improved the performance of the watermarking technique compared to DCT. Experimental results show that modifications to fingerprint image are visually imperceptible and maintain the minutiae detail. The integrity of the fingerprint image is verified through high matching score obtained from the AFIS system. There is also a high degree of correlation between the embedded and extracted watermarks. The degree of similarity is computed using pixel-based metrics and human visual system metrics. It is useful for personal identification and establishing digital chain of custody. The results also show that the proposed watermarking technique is resilient to common image modifications that occur during electronic fingerprint transmission.
Recommended Citation
Tungala, Nikhil C., "Contextual biometric watermarking of fingerprint images" (2004). Graduate Theses, Dissertations, and Problem Reports. 1566.
https://researchrepository.wvu.edu/etd/1566