Optimum scheme selection for face–iris biometric

Abstract

Designing a new dynamic and optimal scheme for face-iris fusion based on the score level, feature level and decision level fusion is considered in this study. Prior to implementing the proposed combined level fusion, several schemes are separately implemented at each level of fusion to investigate the performance improvement of each level of fusion on face and iris modalities. In fact, the optimum scheme is constructed by selecting flexible and dynamic features and scores of face and iris biometrics and then combining the advantages of different levels of fusion. Consequently, the scheme produces a set of fast and flexible features and scores for fusion. On the other hand, the idea of threshold-optimised decisions is used in this study to fuse the optimised decisions of face and iris biometrics. Experimental results on verification rates demonstrate a significant improvement of proposed combined level fusion scheme over unimodal and multimodal fusion methods.

Effect of face and ocular multimodal biometric systems on gender classification

“…Finally, we can conclude this work as a robust face-ocular multimodal biometric system to predict the gender of individuals by reducing the average of search time in multimodal biometric systems. Table 5 Comparison of proposed method with State-of-theart fusion techniques on CASIA-Iris-Distance dataset Fusion techniques Prediction rate Score level fusion min rule [28] 83.00 ± 0.39 max rule [28] 83.00 ± 0.90 weighted sum rule [13] 85.00 ± 0.50 product rule [25] 85.00 ± 0.74 Feature level fusion multiple kernel learning [39] 86.00 ± 0.64 Decision level fusion AND rule [33] 83.00 ± 0.81 majority voting (MV) [40] 83.00 ± 0.73 OR rule [33] 84.00 ± 0.52 threshold optimised AND rule [41] 85.00 ± 0.57 threshold optimised OR rule [41] 86.00 ± 0.66 Proposed scheme 88.00 ± 0.94…”

“…The fusion of information for this kind of system is done at four different levels such as sensor level, match score level, feature level, and decision level fusion [24]. This study takes into account the consideration of match score level and feature level fusion to predicate gender of individuals due to the ease in accessing, fusing and providing high recognition performance [25][26][27][28][29][30][31][32][33]. Match score level fusion considers three different categories to fuse the scores, namely transformation-based score fusion, classifier-based score fusion, and density-based score fusion.…”

A Novel Technique to Enhance Performance of Multibiometric Framework using Bin based Classifier Based on Multi-algorithm Score Level Fusion

“…A GAR of 98.03% and TER of 0.27% is reported trough the experimental result based on the proposed study. An optimum scheme selection for face and iris biometric was proposed by Eskandari and Sharifi [29] in 2016; in this study, they investigate the performance of various combination rules (feature level, score level and decision level) on face and iris modality. In this study threshold optimizes decision is utilized to combine the face and iris biometrics optimal decision.…”

Score-Level-based Face Anti-Spoofing System Using Handcrafted and Deep Learned Characteristics

“…Currently, the use of biometric recognition systems in term of identification and/or verification of individuals according to their physical or behavioral characteristics is extensively studied in situations with high security demands [1][2][3][4][5][6][7][8][9][10]. In fact, the ability of biometrics to improve recognition performance and security of applications considered as increasing interest of researchers compared to conventional techniques such as token-based and knowledge-based methods.…”