Combining Face and Iris Biometrics for Identity Verification

By Yunhong Wang, Tien-Ping Tan, Anil K. Jain. International Conference on Audio- and Video-Based Biometric Person Authentication, 2003

390 citations recorded by the source corpus.

Face and iris identification have been employed in various biometric applications. Besides improving verification performance, the fusion of these two biometrics has several other advantages. We use two different strategies for fusing iris and face classifiers. The first strategy is to compute either an unweighted or weighted sum and to compare the result to a threshold. The second strategy is to treat the matching distances of face and iris classifiers as a two-dimensional feature vector and to use a classifier such as Fisher's discriminant analysis and a neural network with radial basis function (RBFNN) to classify the vector as being genuine or an impostor. We compare the results of the combined classifier with the results of the individual face and iris classifiers.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/b80e866c4565cbcc0f8f793b8db782c7b0ee59da

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Evaluation of biometric spoofing in a multimodal system (2010, background): “We compare three different fusion schemes, all of them operating at the matching score level: 1) Weighted Sum - Some works [14][20] have shown that the sum fusion presents good results even when compared with more sophisticated methods like neural networks [20] and decision trees [14].”
Anti-spoofing in Action: Joint Operation with a Verification System (2013, background): “Examples of these learning-based fusion rules are k-means or fuzzy clustering [6], Support Vector Machines (SVM) [4], [11], Linear Discriminant Analysis (LDA) [4], [23], [26], decision trees [4], [23], multi-layer perceptron [4], [26], Behavior Knowledge Space [22], [25] and many more.”
Robustness of multimodal biometric fusion methods against spoof attacks (2009, background): “Many fusion methods have being recently proposed [2] [3] [4] [5] [6] [7], being that all them show that multimodal biometric systems can significantly increase the recognition rates when compared to unimodal biometric systems.”
Improving Iris Recognition Performance Using Segmentation, Quality Enhancement, Match Score Fusion, and Indexing (2008, background): “In [33] , [35], [36], [52], it has been suggested that the fusion of match scores from two or more classifiers provides better performance compared to a single classifier.”
Score normalization in multimodal biometric systems (2005, methodology): “Wang et al. [15] consider the matching scores at the output of face and iris recognition modules as a two-dimensional feature vector, and use Fisher's discriminant analysis and a neural network classifier with radial basis function for classification .”