A Novel Optimized Deep Network for Ear Detection and Occlusion Analysis DOI
V. Ratna Kumari, P. Rajesh Kumar,

B. Leela Kumari

et al.

Wireless Personal Communications, Journal Year: 2023, Volume and Issue: 131(3), P. 1721 - 1743

Published: May 30, 2023

Language: Английский

Single-sample face and ear recognition using virtual sample generation with 2D local patches DOI
Vivek Tomar, Nitin Kumar

The Journal of Supercomputing, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 30, 2024

Language: Английский

Citations

1
Csa-gru: a hybrid CNN and self attention GRU for human identification using ear biometrics DOI
Anshul Mahajan, Sunil Kumar Singla

Evolving Systems, Journal Year: 2023, Volume and Issue: 15(4), P. 1197 - 1218

Published: Dec. 16, 2023

Language: Английский

Citations

1
Comparative Analysis of Security-Focused Blockchain Architectures: Optimising Security in IoT DOI
Cherif Benali

Published: April 24, 2024

The Internet of Things (IoT) poses serious security risks and issues due to its growing number linked devices. This paper conducts a comparative analysis various security-focused Blockchain-based architectures, exploring their potential optimize in IoT applications. study investigates how designs handle concerns trade-offs, such as integration problems, privacy, scalability, by analyzing comparing essential key features. work tries determine the best approaches for optimizing particular applications assessing different threats. provides insights into suitability Blockchain architectures specific needs contributes ongoing development secure trustworthy ecosystems.

Language: Английский

Citations

0
Advancing Biometric Identity Recognition with Optimized Deep Convolutional Neural Networks DOI Creative Commons
Hammam Alshazly, Hela Elmannai,

Reem Ibrahim Alkanhel

et al.

Traitement du signal, Journal Year: 2024, Volume and Issue: 41(3), P. 1405 - 1418

Published: June 26, 2024

Biometric identity recognition, capitalizing on unique physical attributes, represents an increasingly explored research field within the biometrics community, with implications spanning surveillance, crowd analytics, automated checks, and user device access.Ear images, in particular, offer a robust data source for devising effective personal identification systems.The biometric has seen surge application of machine learning algorithms, specifically deep neural network architectures such as Convolutional Neural Networks (CNNs) transfer methods, to enhance ear recognition systems.This study evaluates leading CNN -ResNet, DenseNet, MobileNet, Inception -for their efficacy creating systems resilient varying imaging conditions.The AMI WPUT datasets, publicly accessible image were utilized train assess proposed models.The models demonstrated substantial success, achieving rank-1 accuracies 96% 83% respectively.Additionally, Gradient-weighted Class Activation Mapping (Grad-CAM) visualization technique was employed elucidate models' decision-making processes, revealing reliance auxiliary features like hair, cheek, or neck when available.The use Grad-CAM not only enhances understanding processes CNNs but also highlights potential areas improvement systems.

Language: Английский

Citations

0
On Authentication in Virtual Reality Environments for Rehabilitation and Psychotherapy Systems DOI
Florina Ungureanu,

Bianca Andreea Bordea,

Robert Gabriel Lupu

et al.

IFMBE proceedings, Journal Year: 2024, Volume and Issue: unknown, P. 279 - 286

Published: Jan. 1, 2024

Language: Английский

Citations

0
Additional Biometric Traits DOI
Anil K. Jain, Arun Ross, Karthik Nandakumar

et al.

Texts in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 245 - 287

Published: Oct. 30, 2024

Language: Английский

Citations

0
DANNET: deep attention neural network for efficient ear identification in biometrics DOI Creative Commons
Deepthy Mary Alex, Kurniawan Teguh Martono, Hanan Abdullah Mengash

et al.

PeerJ Computer Science, Journal Year: 2024, Volume and Issue: 10, P. e2603 - e2603

Published: Dec. 18, 2024

Biometric identification, particularly ear biometrics, has gained prominence amidst the global prevalence of mask-wearing, exacerbated by COVID-19 outbreak. This shift highlighted need for reliable biometric systems that can function effectively even when facial features are partially obscured. Despite numerous proposed convolutional neural network (CNN) based deep learning techniques detection, achieving expected efficiency and accuracy remains a challenge. In this manuscript, we propose sophisticated method named encoder-decoder ensemble technique incorporating attention blocks. innovative approach leverages strengths architectures mechanisms to enhance precision reliability detection segmentation. Specifically, our employs an two YSegNets, which significantly improves performance over single YSegNet. The use is crucial in biometrics due variability complexity shapes potential partial occlusions. By combining outputs capture wider range reduce risk false positives negatives, leading more robust accurate segmentation results. Experimental validation was conducted using combination data from EarVN1.0, AMI, Human Face datasets. results demonstrate effectiveness approach, framework 98.93%. high level underscores practical applications identification. demonstrates significant individual recognition, scenarios involving large gatherings. When complemented effective surveillance system, contribute improved security identification processes public spaces. research not only advances field but also provides viable solution context mask-wearing other obstructions.

Language: Английский

Citations

0
A Novel Optimized Deep Network for Ear Detection and Occlusion Analysis DOI
V. Ratna Kumari, P. Rajesh Kumar,

B. Leela Kumari

et al.

Wireless Personal Communications, Journal Year: 2023, Volume and Issue: 131(3), P. 1721 - 1743

Published: May 30, 2023

Language: Английский

Citations

0