期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2014
卷号：61
期号：3
出版社：Journal of Theoretical and Applied
摘要：Image Fusion is a process of integrating multiple images into a single image.Biometric features are used to provide authentication and security of systems. This paper deals with a new work that implements fusion of biometric features like iris and palmprint. The iris and palmprint are transformed into the set of features independently. The extracted modalities are fused by different fusion algorithm techniques like the pyramid based algorithms and wavelet based algorithms. The quality of fused images is assessed using metrics such as Visual information fidelity, Qabf, Peak Signal Noise Ratio, Mutual Information, Mean Square Error, Normalized Absolute Error, Normal Correlation Coefficient, Cross entropy and Relative Warp. Comparative evaluation of fused images is a critical step to evaluate the relative performance of different image fusion methods. The fused template can be further used in applications like watermarking,person identification system.
关键词：Biometrics; Feature extraction;Fusion metrics; Image fusion; Peak Signal Noise Ratio(PSNR); Mutual Information(MI); Mean Square Error(MSE); Standard Deviation(SD); Root Mean Square Error(RMSE)
