Uploaded by Mogith Pushparaj

AI Project

advertisement
AI Project
Face Recognition Based Attendance System
The system is developed for deploying an easy and a secure way of taking down attendance. The
software first captures an image of all the authorized persons and stores the information into database.
The system then stores the image by mapping it into a face coordinate structure. Next time whenever
the registered person enters the premises the system recognizes the person and marks his attendance
along with the time.
Advantages
•
The software can be used for security purposes in organizations and in secured zones.
•
The software stores the faces that are detected and automatically marks attendance.
•
The system is convenient and secure for the users.
•
It saves their time and efforts.
Disadvantages
•
The system doesn’t recognize properly in poor light so may give false results.
•
It can only detect face from a limited distance.
A face recognition-based attendance system using Python uses computer vision and machine learning
techniques to automatically record attendance by identifying individuals' faces. This AI model is made
using advanced python libraries. There are many steps involved in this process. Following are the steps
involved :
Data Collection:
The first step is to gather a dataset of facial images for each individual whose attendance needs to be
tracked. These images should cover different lighting conditions, angles, and facial expressions to
improve the model's accuracy.
Preprocessing:
The collected images are preprocessed to enhance the quality and consistency of the data. This may
involve resizing, normalization, and other techniques to prepare the images for the model.
Feature Extraction:
A common approach is to use a pre-trained deep learning model, such as a Convolutional Neural
Network (CNN), to extract facial features from the images. The deep network learns to identify unique
patterns in the faces that are relevant for recognition.
Face Encoding:
Once the features are extracted, they are transformed into a numerical representation known as a face
embedding or encoding. This encoding captures the essential characteristics of a face in a compact
format.
Attendance Database:
A database is set up to store the face encodings along with the corresponding individuals' information
(e.g., names, IDs, etc.). This database serves as a reference during the recognition process.
Recognition:
When marking attendance, the system captures a live video stream from a camera. The faces detected
in each frame are localized and extracted.
Face Matching:
For each extracted face, the system calculates its face embedding using the same feature extraction
process used during training. It then compares this embedding with the encodings in the attendance
database to identify the closest match.
Thresholding:
The system defines a similarity threshold to determine whether the extracted face's encoding is a match
with any of the stored encodings. If the similarity is above the threshold, the individual is considered
recognized.
Marking Attendance:
Once a recognized face is confirmed, the system records the attendance by associating it with the
corresponding individual in the attendance database. This could involve updating a timestamp or other
attendance-related information.
User Interface:
The system might include a user interface (UI) to display recognized individuals, capture real-time video,
and show attendance records. The UI can also provide administrators with the ability to manage the
attendance database.
Download