On the Effect of Score Equalization in SVM Multimodal Biometric Systems
نویسندگان
چکیده
Most Support Vector Machine (SVM) based systems make use of conventional methods for the normalization of the features or the scores previously to the fusion stage. In this work, in addition to the conventional methods, two equalization methods, histogram equalization, which was recently introduced in multimodal systems, and Bi-Gaussian equalization, which is presented in this paper, are applied upon the scores in a multimodal person verification system composed by prosodic, speech spectrum, and face information. The equalization techniques have obtained the best results; concretely, Bi-Gaussian equalization outperforms in more than a 22.19 % the results obtained by Min-Max normalization, the most used normalization technique in SVM fusion systems. The prosodic and speech spectrum scores have been provided by speech experts using records of the Switchboard I database and the face scores have been obtained by a face recognition system upon XM2VTS database.
منابع مشابه
Performance evaluation of score level fusion in multimodal biometric systems
In a multimodal biometric system, the effective fusion method is necessary for combining information from various single modality systems. In this paper the performance of sum rule-based score level fusion and support vector machines (SVM)-based score level fusion are examined. Three biometric characteristics are considered in this study: fingerprint, face, and finger vein. We also proposed a n...
متن کاملScore level Fusion based Multimodal Biometric Identification
Feature level based monomodal biometric systems perform person recognition based on a multiple sources of biometric information and are affected by problems like integration of evidence obtained from multiple cues and normalization of features codes since they are heterogeneous, in addition of monomodal biometric systems problems like noisy sensor data, non-universality and lack of individualit...
متن کاملBi-Gaussian score equalization in an audio-visual SVM-based person verification system
In multimodal fusion systems a normalization of the features or the scores is needed before the fusion process. In this work, in addition to the conventional methods, histogram equalization, which was recently introduced by the authors in multimodal systems, and Bi-Gaussian equalization, which takes into account the separate statistics of the genuine and impostor scores, and is introduced in th...
متن کاملFusion strategies in multimodal biometric verification
The aim of this paper, regarding multimodal biometric verification, is twofold: on the one hand, to review some score fusion strategies reported in the literature and, on the other hand, to compare experimentally a selection of them using as monomodal baseline systems our template-based face, minutiaebased fingerprint and HMM-based on-line signature verification systems on the MCYT multimodal d...
متن کاملMultimodal Person Authentication using Qualitative SVM with Fingerprint, Face and Teeth Modalities
Multimodal biometrics systems are becoming increasingly efficient over the unimodal system, especially for the securing handheld devices. However, the challenge with this authentication system is the relative degradation of the biometric modalities involved in the development and test data respectively. To overcome this problem, in this paper we propose a novel Qualitative Support Vector Machin...
متن کامل