Genetic programming for multibiometrics

Abstract

Biometric systems suffer from some drawbacks: a biometric system can provide in general good performances except with some individuals as its performance depends highly on the quality of the capture... One solution to solve some of these problems is to use multibiometrics where different biometric systems are combined together (multiple captures of the same biometric modality, multiple feature extraction algorithms, multiple biometric modalities. . . ). In this paper, we are interested in score level fusion functions application (i.e., we use a multibiometric authentication scheme which accept or deny the claimant for using an application). In the state of the art, the weighted sum of scores (which is a linear classifier) and the use of an SVM (which is a non linear classifier) provided by different biometric systems provid one of the best performances. We present a new method based on the use of genetic programming giving similar or better performances (depending on the complexity of the database). We derive a score fusion function by assembling some classical primitives functions (+, * , −, ...). We have validated the proposed method on three significant biometric benchmark datasets from the state of the art. Every day, new evolutions are brought in the biometric field of research. 3 These evolutions include the proposition of new algorithms with better per-4 formances, new approaches (cancelable biometrics, soft biometrics, ...) and 5 even new biometric modalities (like finger knuckle recognition [1], for example). 6 There are many different biometric modalites, each classified among three main 7 families (even if we can find a more precise topology in the literature) : 8 • biological : recognition based on the analysis of biological data linked to an 9 individual (e.g., DNA analysis [2], the odor [3], the analysis of the blood 10 of different physiological signals, as well as heart beat or EEG [4]); 11 • behavioural : based on the analysis of an individual behaviour while he is 12 performing a specific task (e.g., keystroke dynamics [5], online handwrit-13 ten signature [6], the way of using the mouse of the computer [7], voice 14 recognition [8], gait dynamics (way of walking) [9] or way of driving [10]); 15 • morphological based on the recognition of different particular physical pat-16 terns, which are, for most people, permanent and unique (e.g., face recog-17 nition [11], fingerprint recognition [12], hand shape recognition [13], or 18 blood vessel [14], ...). 19Nevertheless, there will always be some users for which a biometric modality 20 (or method applied to this modality) gives bad results, whereas, they are better 21 in average. These low performances can be implied by different facts: the quality 22 of the capture, the instant of acquisition and the individual itself but they have 23 the same implication (impostors can be accepted or user need to authenticate 24 themselves several times on the system before being accepted). Multibiometrics 25 allow to solve this problem while obtaining better perf...

Fast computation of the performance evaluation of biometric systems: Application to multibiometrics

“…We can note that the generated function all generate a monotonically decreasing ROC curve which allows to use our method. If the ROC curve does not present this shape, we would be unable to Figure 9: ROC Curve Of The Generated Multibiometrics Fusion Functions on the Validation Set of the BSSR1 dataset obtain the estimated EER (such drawbacks as been experimented using genetic programming [41] instead of genetic algorithms).…”

gb2s μ MOD: A MUltiMODal biometric video database using visible and IR light

“…The selection of the best weights is an intractable task due to the amount of comparisons needed. A genetic program [35] was developed to optimize these weights minimizing a fitness function in a finite number of steps, in this case 20 iterations. Intersession experiments under controlled conditions have been driven using the palm-side hand video subsets corresponding to each of the available light spectrum sectors, visible light and infrared light at 850 nm.…”

A Survey of Wearable Biometric Recognition Systems

“…Decision fusion algorithms can also be generated through machine learning. Giot and Rosenberger [2012] experimented with genetic programming [Koza 1992] to generate the fusion function, but results were only slightly better than weighted sums. found that combining 12-lead ECG signals at decision level performed better than fusion at the feature level.…”