With the wide spread utilization of Biometric identification systems, establishing the authenticity of biometric data itself has emerged as an important issue. In this chapter, a novel approach for creating a multimodal biometric system has been suggested. The multimodal biometric system is implemented using the different fusion schemes such as Average Fusion, Minimum Fusion, Maximum Fusion, Principal Component Analysis Fusion, Discrete Wavelet Transform Fusion, Stationary Wavelet Transform Fusion, Intensity Hue Saturation Fusion, Laplacian Gradient Fusion, Pyramid Gradient Fusion and Sparse Representation Fusion. In modality extraction level, the information extracted from different modalities is stored in vectors on the basis of their modality. These are then blended to produce a joint template which is the basis for the watermarking system. The fused image is applied as input along with the cover image to the Genetic Algorithm based Bacterial Foraging Optimization Algorithm watermarking system. The standard images are used as cover images and performance was compared.
TopIntroduction
Digital watermarking is the technology of embedding information (i.e., watermark or host image) into the multimedia data (such as image, audio, video, and text), called cover image. It is realized by embedding data that is invisible to the human visual system into a host image. Hence, the term digital image watermarking is a procedure by which watermark data is covered inside a host image which imposes imperceptible changes to the picture. Watermarking techniques have been used in multimodal biometric systems for the purpose of protecting and authenticating biometric data and enhancing accuracy of identification. A multimodal biometric system combines two or more biometric data recognition results such as a combination of a subject's fingerprint, face, iris and voice. This increases the reliability of personal identification system that discriminates between an authorized person and a fraudulent person.
Multimodal biometric system has addressed some issues related to unimodal such as, (a) Non-universality or insufficient population coverage (reduce failure to enroll rate which increases population coverage). (b) It becomes more and more unmanageable for an impostor to imitate multiple biometric traits of a legitimately enrolled individual. (c) Multimodal-biometric systems effectively address the problem of noisy data (illness affecting voice, scar affecting fingerprint).
In this chapter, a novel approach for creating a multimodal biometric system has been proposed. The multimodal biometric system is implemented using the different fusion schemes such as Average Fusion, Minimum Fusion, Maximum Fusion, PCA Fusion, DWT Fusion, SWT Fusion, IHS Fusion, Laplacian Gradient Fusion, Pyramid Gradient Fusion and Sparse Representation Fusion to improve the performance of the system. In feature extraction level, the information extracted from different modalities is stored in vectors on the basis of their modality. These modalities are then blended to produce a joint template which is the basis for the watermarking system. Fusion at feature extraction level generates a homogeneous template for fingerprint, iris and palmprint features. The fused image is applied as input along with the cover image to the GA based BFOA watermarking system.