Article Sidebar
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
As an open access journal, copyright on Anchor University Journal of Science and Technology (AUJST) is retained by the author(s). Authors grant AUJST a license to publish the article and identify itself as the original publisher. Authors also grant any third party the right to use the article freely as long as its integrity is maintained and its original authors, citation details and publisher are identified.
Main Article Content
Multimodal Biometric Image Fusion Using Discrete Wavelet Transform Method
Abstract
Background: Security is a key component to every application in the modern world. One of the most effective methods for ensuring security in many sectors is the use of personal characteristics.
Objectives: The objective of this study is to enhance the accuracy and robustness of biometric recognition through the utilization of a Discrete Wavelet Transform-based multimodal image fusion approach.
Methods: Multimodal biometric techniques were designed to resolve unimodal biometrics' deficiencies. In this research, discrete wavelet transform (DWT)-based multimodal fusion algorithms are proposed, in which database images are fused. Face, iris images and fingerprint are fused and the performance metric of different decomposition level were determined.
Result: This work provides a comparison of various decomposition filters for face, iris and fingerprint fused images. The result of metric performance on the fused images showed that the fused of face-iris have the highest value of entropy and principal component analysis which imply quality information to the source image.
Conclusion: The per for mance of DWT fusion techniques show that it provides better spatial and spectral localization of image information
