Identifikasi Pembuluh Darah Jari Tangan, Menggunakan Bahasa Pemrograman Python

Abstract

Biometric systems automatically identify people based on their behavioral characteristics. Finger veins are more secure as biometric data than other biometric data. Finger vein patterns are difficult to forge because they are below the surface of the skin. To make the vascular pattern visible on the skin, a special method is needed to identify it. This research aims to develop a finger vein recognition system using the Convolutional Neural Network (CNN) method implemented in Python, with the aim of replacing the fingerprint-based employee attendance system in hospitals. This method offers higher security and resistance to forgery, given that finger veins are difficult to access from outside the body. This research utilizes the blood vessel dataset from Kaggle and goes through three main stages: preprocessing, training, and testing. The trained CNN model showed high performance with 99.99% accuracy in recognizing patterns in the finger vein images. The results of this study confirm that the developed system can provide accurate