Face Recognition Using Haar Cascade

Abstract

The Face Recognition System using Haar Cascade and LBPH Algorithm is an intelligent computer vision-based application designed to detect and recognize human faces through a webcam. In the present digital era, face recognition technology plays an important role in security, authentication, surveillance, attendance management, and identity verification. Traditional identification methods such as ID cards, passwords, and manual attendance registers are time-consuming and may lead to errors, proxy attendance, or unauthorized access. To overcome these limitations, the proposed system provides an automated and contactless method for identifying registered persons using facial features. The system is developed using Python, OpenCV, Flask, Haar Cascade Classifier, and LBPH Face Recognizer. Haar Cascade is used to detect the human face from the live camera frame, while the LBPH algorithm is used to recognize the detected face by comparing it with trained face data. The system first collects face samples of registered users through the webcam and stores them in separate dataset folders. After collecting sufficient face images, the model is trained and saved for future recognition. During recognition, the webcam captures the live face, detects the face region, compares it with the trained model, and displays the recognized person’s name along with the confidence value. The project also includes a simple web-based interface developed using Flask, which allows users to collect face data, train the model, start face recognition, stop recognition, view registered persons, and check recognition logs. The system maintains a record of recognized persons with time and confidence details. The proposed solution reduces manual effort, improves identification accuracy, and provides a low-cost face recognition system suitable for academic institutions, offices, laboratories, and small organizations. Overall, this project demonstrates the practical use of computer vision and machine learning techniques for real-time face detection and recognition.