A comprehensive overview of biometric fusion

Singh, Maneet; Singh, Richa; Ross, Arun

doi:10.1016/j.inffus.2018.12.003

Cited by 170 publications

(79 citation statements)

References 197 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hot topics integrating data quality, soft biometrics, approaches to enhance the accuracy of biometric recognition to prevent security attacks using cryptosystems were also discussed. Authors concluded their review while addressing the research challenges concerning biometric based fusion systems [18]. Gunasekaran et al (2019) proposed a biometric recognition system that used Contour let Transform Model for pre-processing followed by Local Derivative Ternary Pattern model to improve recognition based on pre-processed features.…”

Section: Singh Et Al (2019)mentioning

confidence: 99%

Novel Biometric Fusion System using GA-PSO and ANN

Kaur*

2020

IJITEE

View full text Add to dashboard Cite

Technology advancements have led to the emergence of biometrics as the most relevant future authentication technology. On practical grounds, unimodal biometric authentication systems have inevitable momentous limitations due to varied data quality and noise levels. The paper aims at investigating fusion of face and fingerprint biometric characteristics to achieve a high level personal authentication system. In the fusion strategy face features are extracted using Scale-Invariant Feature Transform (SIFT) algorithm and fingerprint features are extracted using minutiae feature extraction. These extracted features are optimized using nature inspired Genetic Algorithm (GA). The efficiency of the proposed fusion authentication system is enhanced by training and testing the data by applying Artificial Neural Network (ANN). The quality of the proposed design is evaluated against two nature inspired algorithms, namely, Particle Swarm Optimization (PSO)and Artificial Bee Colony (ABC) in terms of False Acceptance Rate (FAR), False Rejection Rate (FRR) and recognition accuracy. Simulation results over a range of image sample from 10 to 100 images have shown that the proposed biometric fusion strategy resulted in FARof 2.89, FAR 0.71and accuracy 97.72%.Experimental evaluation of the proposed system also outperformed the existing biometric fusion system.

show abstract

Section: Singh Et Al (2019)mentioning

confidence: 99%

Novel Biometric Fusion System using GA-PSO and ANN

Kaur*

2020

IJITEE

View full text Add to dashboard Cite

show abstract

“…AlexNet is considered as the first state-of-the-art deep learning approach after it outperformed traditional computer vision methods in terms of accuracy and recognition rates [41]. It is the most well-studied CNN architecture due to its impact in most image classification tasks [42]. The architecture and network design of AlexNet is composed of 8 sequential layers with ~60 million parameters for a total of 25 layers.…”

Section: ) Alexnetmentioning

confidence: 99%

Unconstrained Ear Recognition through Domain Adaptive Deep Learning Models of Convolutional Neural Network

Alejo¹,

Hate²

2019

IJRTE

View full text Add to dashboard Cite

Limited ear dataset yields to the adaption of domain adaptive deep learning or transfer learning in the development of ear biometric recognition. Ear recognition is a variation of biometrics that is becoming popular in various areas of research due to the advantages of ears towards human identity recognition. In this paper, handpicked CNN architectures: AlexNet, GoogLeNet, Inception-v3, Inception-ResNet-v2, ResNet-18, ResNet-50, SqueezeNet, ShuffleNet, and MobileNet-v2 are explored and compared for use in an unconstrained ear biometric recognition. 250 unconstrained ear images are collected and acquired from the web through web crawlers and are preprocessed with basic image processing methods including the use of contrast limited adaptive histogram equalization for ear image quality improvement. Each CNN architecture is analyzed structurally and are fine-tuned to satisfy the requirements of ear recognition. Earlier layers of CNN architectures are used as feature extractors. Last 2-3 layers of each CNN architectures are fine-tuned thus, are replaced with layers of the same kind for ear recognition models to classify 10 classes of ears instead of 1000. 80 percent of acquired unconstrained ear images is used for training and the remaining 20 percent is reserved for testing and validation. Results of each architectures are compared in terms of their training time, training and validation outputs as such learned features and losses, and test results in terms of above-95% accuracy confidence. Above all the used architectures, ResNet, AlexNet, and GoogleNet achieved an accuracy confidence of 97-100% and is best for use in unconstrained ear biometric recognition while ShuffleNet, despite of achieving approximately 90%, shows promising result for use in mobile version of unconstrained ear biometric recognition.

show abstract

“…The previous two decades have seen the improvement of an extensive number of biometric and multi biometric cryptosystems which was talked about for the acknowledgment of a person for security reason. Maneet Singh et al [13] have exhibited an outline of biometric combination with explicit spotlight on three inquiries: what to fusion, when to wire, and how to interlink. A complete survey of methods fusing auxiliary data in the biometric acknowledgment pipeline was additionally introduced.…”

Section: A Submission Of the Papermentioning

confidence: 99%

Cryptographic Algorithm based Feature Level Fusion of Fingerprint and Iris in a Multi-Biometric Recognition System

Jayapriya*,

2019

IJITEE

View full text Add to dashboard Cite

Biometric encryption is one of the developing exploration area, which is a strategy for merging biometric features with cryptographic keys. Biometric Recognition is based on the anatomical and behavior attributes of the individuals. Multibiometric is the combination of various biometrics like Fingerprint, Iris, and Face, Fingervein etc. Experts are concentrating on the most proficient method to give security to the framework, the template which was produced from the biometric should be ensured. The main objective of this paper is to protect the multi biometric template by creating a protected sketch by deploying bio cryptosystem. Once the biometric template is stolen it turns into a major issue for the security of the framework and furthermore for client protection. In this way, a bio-crypto framework ensures the confidentiality of the information. In this paper bio cryptosystem is proposed to improve the security of multimodal frameworks by producing the biocrypto key from Finger print and iris. Gray level co-occurrence matrix (GLCM) based Haralick features, local binary pattern (LBP), triplet half-band filter bank (THFB) and dynamic features (DF) are extracted from fingerprint and iris. The high dimensionality space of the features are reduced using kernel principal component analysis (KPCA. Finally, the encoding process is matted with biometric key utilizing symmetric RSA (Rivest-Shamir-Adleman) cryptographic algorithm.

show abstract

A comprehensive overview of biometric fusion

Cited by 170 publications

References 197 publications

Novel Biometric Fusion System using GA-PSO and ANN

Novel Biometric Fusion System using GA-PSO and ANN

Unconstrained Ear Recognition through Domain Adaptive Deep Learning Models of Convolutional Neural Network

Cryptographic Algorithm based Feature Level Fusion of Fingerprint and Iris in a Multi-Biometric Recognition System

Contact Info

Product

Resources

About