Utilizing Convolutional Neural Networks for Fingerprint-Based Attendance Monitoring
Journal Title: International Journal of Multidisciplinary Research and Analysis - Year 2023, Vol 6, Issue 04
Abstract
The traditional method of taking attendance using paper sheets is prone to errors like impersonation, loss, or theft. To solve this issue, automatic attendance systems utilizing identification technology such as barcode badges, electronic tags, touch screens, magnetic stripe cards, and biometrics have been implemented. Biometric technology uses physiological or behavioral characteristics for identification purposes, but traditional biometric systems have limitations such as vulnerability to damage or alteration over time, and variations in occlusions, poses, facial expressions, and illumination can affect face recognition accuracy. Fingerprint identification relies on the distinctiveness of fingerprints and involves comparing two impressions of the friction ridges on human fingers or toes to determine if they belong to the same individual. There are five primary categories of fingerprints: arch, tented arch, left loop, right loop, and whorl. Various algorithms have been developed to recognize fingerprints using minutiaebased matching, which involves identifying key features like ridge ending and bifurcation. Deep learning algorithms, particularly convolutional neural networks, have been successful in improving identification accuracy by extracting features automatically from fingerprint images. In recent times, securing personal data has become increasingly important, and the Convolutional Neural Network (CNN) identification system is recommended for improving accuracy and performance. This paper proposes a fingerprint identification system that combines three models: CNN, Softmax, and Random Forest (RF) classifiers. The conventional system uses K-means and DBSCAN algorithms to separate the foreground and background regions and extracts features using CNNs and dropout approach. The Softmax acts as a recognizer. The proposed algorithm is evaluated on a public database and shows promising results, providing an accurate and efficient biometric identification system.
Authors and Affiliations
King Bernard S. Saul, Joy B. Saul, Kristine T. Soberano
Keywords
Related Articles
- EP ID EP714873
- DOI 10.47191/ijmra/v6-i4-03
- Views 81
- Downloads 0
The Criminal Action of Rape Against Child According to Indonesian Law Number 35 of 2014
Currently the Indonesian people are actively working on fixing very important issues regarding Human Rights (HAM) in all aspects of life, especially child protection in Indonesia. The criminal act of rape against a child...
Development of Vertical Axis Wind Turbine Charger as Alternative Power Source
The study was focused on the development of Vertical Axis Wind Turbine Charger with D.C Air Compressor to address power shortage in the coastal area in the Province of Isabela. This project development research tried to...
Formation of Baked Yarn of Complex Structure, Methods for Determining The Hairiness of The Yarn and Hair Characteristics
This paper examines the differences between the main purpose of the process of falling from individual fibers in a given linear density, density and elasticity and the methods of determining the hairiness of the yarn, th...
Meritocracy Disguised as Equity: The Relationship between Teacher Professional Organizations and Teacher Ideology
The institution of public schooling in the United States exists in the popular imagination as a primary means of achieving social mobility. It is believed that schools provide students with unbiased opportunities to ear...
21st Century Learning Skills, Study Habits, and the Mathematics Performance of Grade 7 Students
This study examined the study habits, 21st-century learning skills, and mathematics performance of 132 Grade 7 students at Santa Maria National High School in the 2021-2022 school year. It looked at the kids' characteris...