Abstract

In today's rapidly evolving world, security has become a paramount concern. Biometric-based methods have emerged as a reliable and accurate means of authentication, with hand-based biometric traits being easily accessible for data collection. In this paper, we present a novel approach for authentication utilizing finger-vein images, addressing the challenges of collecting and processing biometric trait images for large organizations. However, the collection, storage, and processing of biometric trait images for a large number of employees pose significant challenges. To overcome these challenges, our proposed approach leverages deep learning techniques to authenticate individuals based on finger-vein images. The rise in technological advancements has brought about an elevated risk to both personal data and national security. Existing methods designed to safeguard crucial information from external threats were found to be insufficient. There emerged a necessity to implement more advanced technologies that could ensure a higher level of efficiency in protecting our data from unauthorized access. In this proposed method we use Sobel filter , open cv and gaussian blur for image pre-processing, sequential model with transfer learning for feature extraction and finally, Adam optimizer for decision making. The proposed model has shown 98% accuracy in authenticating finger veins. Keywords: Sobel Filter, Open CV, Sequential Model, Transfer Learning, Adam Optimiser.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.