Smart Attendance Automation Using Camera-Based Face Recognition

Attendance management in educational institutions is often performed through manual registers or roll calls, which require staff time and can lead to recording errors, proxy attendance, and difficulty retrieving historical records. This paper presents a web-based Smart Attendance Automation prototype that integrates camera-based face detection and recognition with digital attendance management. The application is developed using Python and Flask, with HTML, CSS, Bootstrap, and JavaScript for the user interface and SQLite for student and attendance records. During enrollment, an administrator enters student details and captures ten facial images per student. The images are organized by roll number and used to train an OpenCV Local Binary Patterns Histograms (LBPH) recognizer. During attendance, browser camera frames are sent to the Flask backend, Haar Cascade detects face regions, and LBPH predicts the registered identity. A configured threshold is applied before a student is accepted. The application checks for an existing record before inserting attendance for the same student and date, and provides student management, daily and monthly reports, individual attendance history, charts, and CSV export. Preliminary testing involved six registered students under good and low lighting, and six unregistered people. The system correctly identified 6/6 registered-student attempts under good lighting and 4/6 under low lighting; the remaining two low-light attempts were rejected. All six unregistered-person tests were rejected as unregistered, with no incorrect acceptance observed. The resulting genuine-student identification rate was 83.33%, the false rejection rate was 16.67%, and the observed false acceptance rate was 0% in this small test sample. These results are preliminary and require validation using a larger, more diverse dataset

Authors

Publication Details

Journal
International Journal of Latest Technology in Engineering Management & Applied Science
Published
2026-11-14
DOI
https://doi.org/10.51583/ijltemas.2026.151000105
Primary Topic
Face recognition and analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Smart Attendance Automation Using Camera-Based Face Recognition

V. Jashwanth, S. Karthik, P. Sai Charan, T. Sai Kumar et al.
International Journal of Latest Technology in Engineering Management & Applied Science
Face recognition and analysis
article

Smart Attendance Automation Using Camera-Based Face Recognition

V. Jashwanth, S. Karthik, P. Sai Charan, T. Sai Kumar, Roshan Malga
article en

Abstract

Attendance management in educational institutions is often performed through manual registers or roll calls, which require staff time and can lead to recording errors, proxy attendance, and difficulty retrieving historical records. This paper presents a web-based Smart Attendance Automation prototype that integrates camera-based face detection and recognition with digital attendance management. The application is developed using Python and Flask, with HTML, CSS, Bootstrap, and JavaScript for the user interface and SQLite for student and attendance records. During enrollment, an administrator enters student details and captures ten facial images per student. The images are organized by roll number and used to train an OpenCV Local Binary Patterns Histograms (LBPH) recognizer. During attendance, browser camera frames are sent to the Flask backend, Haar Cascade detects face regions, and LBPH predicts the registered identity. A configured threshold is applied before a student is accepted. The application checks for an existing record before inserting attendance for the same student and date, and provides student management, daily and monthly reports, individual attendance history, charts, and CSV export. Preliminary testing involved six registered students under good and low lighting, and six unregistered people. The system correctly identified 6/6 registered-student attempts under good lighting and 4/6 under low lighting; the remaining two low-light attempts were rejected. All six unregistered-person tests were rejected as unregistered, with no incorrect acceptance observed. The resulting genuine-student identification rate was 83.33%, the false rejection rate was 16.67%, and the observed false acceptance rate was 0% in this small test sample. These results are preliminary and require validation using a larger, more diverse dataset

International Journal of Latest Technology in Engineering Management & Applied ScienceVol. 15(10)
Face recognition and analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon