Multimodal Biometric System Using Fingernail and Finger Knuckle

Abstract

Over many decades lines on hands used for astrological and numerology analysis because there is a trust that Lines never lie. Dorsum of the hand can be very useful in personal identification but yet it has not that much extensive attention. Single scan of dorsum hand can give two biometric traits finger-knuckle and finger nail. This paper presents an approach to combine Finger-knuckle and finger-nail features. Finger nail biometric is considered as quite unique biometric trait hence we combine this trait with finger knuckle.Fingerknuckle features are extracted using Mel Frequency Cepstral Coefficient (MFCC) technique and the features of finger-nail are extracted from second level wavelet decomposition. We combined these features using feature level fusion and feed forward backpropagation neural network for classification. The performance of the system has been tested on our own KVKR-knuckle database that includes 100 subjects dorsal hands. Evaluation results shows that increase in training set gives increased performance rate. The best performance of the proposed system reaches up to 97% with respective training of 90% of total dataset.

System for multimodal biometric recognition based on finger knuckle and finger vein using feature‐level fusion and k‐support vector machine classifier

“…In this section, the literature review concerned with the finger vein and the finger knuckle for the multimodal biometric recognition system [3, 5, 6, 8, 9, 11, 12, 18–24] were discussed. Perumal and Ramachandran [3] presented the local convex direction map of the finger knuckle print (FKP) image for recognition.…”

“…User acceptance is also very high for the finger knuckle and the finger vein compared to the other biometric traits. The performance is also good for the finger knuckle and the finger vein due to the finger geometry [4–6]. In addition to, security, non‐traceability, speed, user friendly, accuracy [7–9] and so on are the advantages of the finger vein.…”

On the use of fingernail images as transient biometric identifiers

“…no longitudinal analysis is performed). The work of [10] combines biometric information from fingernails and finger knuckles to create a multi-modal biometric system. Mel Frequency cepstral coefficients (MFCC) is employed to create a finger knuckle biometric signature.…”

“…Nevertheless, the work does not assess the behaviour of the information over time. In both [10,12] the final signatures are composed from information of three fingers. There is no special fusion methodology to keep transient characteristics of the data.…”

“…T PR = T P T P + FN (10) Conventionally when a biometric methodology is evaluated with a ROC curve, the False Positive Rate ranges from 10 −3 to 1. Given that our datasets compromise 93 subjects (being the first datasets of their kind), evaluating at FPR = 10 −3 would produce results of low statistical significance since the classification of a single subject would greatly alter the output values.…”