Highly secure palmprint based biometric template using fuzzy vault

Abstract

Biometric cryptosystem is an integrated system of cryptography with biometric features which is considered to be a promising component of template security. This paper presents a novel method for biometric cryptosystem based on fuzzy vault using palmprint features. Initially, pre-processing is performed to remove noise in palmprint enrolled image and to pre-align image automatically.Bottom-hat filtering is employed for the feature extraction from the palmprint images. A polynomial is evaluated from the secret key and this polynomial is used to generate projections from palmprint features. Fuzzy vault is created by combining projected points with randomly generated dummy or chaff points. During decoding process, matching scores are calculated by comparing the query feature and stored vault. The vault is successfully decoded when the matched scores should be greater than a predefined threshold value. Experiments were conducted on CASIA database.Simulation result demonstrates that the proposed method gives better performance than other methods and improves the robustness against some security attacks. KEYWORDSbrute force attack, fuzzy vault, palmprint, principal line, security analysis, template protection INTRODUCTIONBiometrics is one of the reliable approaches to measure human individuality with the end goal of authenticating or identifying the character of a core. Palmprint, fingerprint, iris, palm vein, retina, facial features, voice, handwriting, and signatures are commonly used characteristics in person recognition. 1 Among these characteristics, palmprint identification has many advantages: higher acceptance rate, low-resolution image, stable line features, rich texture information, and low intrusiveness. Palms are large in size and palmprint has the features like principal lines, wrinkles, delta point, datum point, minutiae, and creases (a), as shown in Figure 1. 2 Template is a digital representation of the unique feature set that has been obtained from the biometric sample during enrolment process and stored in the system database. It represents a strong link between a person, his/her identity, and these characteristics cannot be easily forged or lost. 3 However, biometric based identification system requires huge volume of biometric information that leads to identity theft and leakage of privacy. Biometric template security has drawn more attention from the researchers. Both biometrics and cryptography have combined in order to address problem of biometric template protection. Various biometric template protection methods have been found in the literature. [4][5][6][7] Biometric cryptosystems have been emerged as a promising tool for biometric template protection. These systems integrate biometric features with the transformed version of cryptographic keys to generate secure biometric template. In biometric cryptosystem, some public information named as helper data is generated. 8 Based on the usage of helper data, biometric cryptosystems can be categorized into two methods, namely, key generation and key...

Touchless palm print recognition system design using Gray Level Co-occurrence Matrix feature with K-Nearest Neighbor classification in MATLAB

“…Equations In RoI extraction, it automatically and reliably clusters small regions of the captured palm that contain a lot of information when the user may pose naturally or deform in other ways, such as rotation, stretching, and scale variability [21,22,23,24]. Thus, RoI is an area localisation stage based on the classification and masking of a selected image part for processing.…”

Privacy Enhancement in Biometric Systems by Template Protection using Deep Learning

“…The fuzzy vault stores the fusion encoding, thereby protecting the information of the feature point and achieving a high value for GAR and a low value for FAR. Chitra and Sujitha enhance the security of the pre-aligned fingerprint template by producing a fuzzy vault by extracted minutiae features and secret key in [15] and for the palmprint biometric template, they created a fuzzy vault by evaluating a polynomial from a secret key with combining the projected points with some randomly generated dummy points [16]. Gilkalaye et al [17] proposed a sphere packing lattice structure scheme in the Euclidean space.…”

A Fingerprint Template Protection Scheme Using Arnold Transform and Bio-hashing

“…Also, some attempts have been made to secure biometric template using Unimodal and multimodal techniques. Unimodal systems use single biometric feature [7,8] while multimodal systems use multiple features [6,9] for template protection. Unimodal biometric systems are cheaper and simple to execute but without a unique method for securing their templates information.…”