A Novel Deep Learning-Based Approach for Palmprint Recognition and Feature Extraction Using BiConvLSTM and Improved Binary Dragonfly Algorithm

Recognition of palm prints has been widely used in security and authentication. Several palmprint recognition techniques have shown promising effectiveness in the last 10 years. However, most of these approaches necessitate extensive prior knowledge and are unsuited for multispectral Recognition of...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:SN computer science Ročník 6; číslo 6; s. 578
Hlavní autori: Nalamothu, Aravind, Rayachoti, Eswaraiah
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Singapore Springer Nature Singapore 01.08.2025
Springer Nature B.V
Predmet:
Accuracy
Algorithms
Biometric recognition systems
Biometrics
Cellular telephones
Computer Imaging
Computer Science
Computer Systems Organization and Communication Networks
Data Structures and Information Theory
Datasets
Deep learning
Effectiveness
Efficiency
Feature extraction
Identification
Image quality
Information Systems and Communication Service
Machine learning
Methods
Mobile commerce
Original Research
Pattern Recognition and Graphics
Security clearances
Software Engineering/Programming and Operating Systems
Vision
BConvLSTM
Improved binary dragonfly algorithm (IBDA)
Palmprint recognition
Matching score
ISSN:2661-8907, 2662-995X, 2661-8907
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Recognition of palm prints has been widely used in security and authentication. Several palmprint recognition techniques have shown promising effectiveness in the last 10 years. However, most of these approaches necessitate extensive prior knowledge and are unsuited for multispectral Recognition of palmprint, contactless, or contact-based scenarios. This issue constrains the applicability and acceptance of palmprint recognition. For feature enhancement in palmprint, we suggested a method for picture contrast enhancement in this research. Initially, in preprocessing, we improve the image quality by employing the CLAHE approach; similarly, a Mean filter is used to smooth the image. Then, the features are extracted using the improved binary dragonfly algorithm (IBDA). The BiConvLSTM algorithm was used to classify the palmprint. To increase the effectiveness of the multifaceted framework, we integrated modalities at the corresponding score level. The suggested technique effectively lowers the number of characteristics and computation time while increasing palmprint identification accuracy. We used the IITD and Tongji datasets to simulate and assess the proposed method. Compared to existing approaches, the proposed method achieved a superior accuracy of 99.18%. The findings demonstrate the suggested strategy's ability to surpass the latest holistic approaches and coded palmprint identification techniques.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2661-8907
2662-995X
2661-8907
DOI:10.1007/s42979-025-04068-0