Location Monitoring Through Face Recognition

Project Title

Location Monitoring Through Face Recognition

Project Area of Specialization Artificial IntelligenceProject Summary

Nowadays that security comes into more prominence every day, it is necessary for people to keep more passwords in their mind and carry more cards with themselves. Such implementations however, are becoming less secure and practical, thus leading to an increasing interest in techniques related to biometrics systems. Biometrics systems are the systems which store physical properties of people in electronic environment and enable them to be recognized by the stored electronic information when needed. Biometrics is the identification of human. It works on the principle of identification of physical properties of a person which he or she cannot alter, are distinctive from others, can be used for identification, and are in his or her possession only. Extensive studies are conducted on biometrics techniques such as fingerprint, hand, face, iris, retina and voice recognition. Some systems have been developed, tested, and results have been obtained. Face recognition systems are among the most important subjects in biometrics systems. These systems, which are very important for security in particular, have been widely used and developed in many countries.

This is a people-tracking project based on face recognition. There will be different cameras in different parts of building. On main entrance, we will take some pictures of people; assign them some id, save record in database. Let’s say there are some areas in building e.g area A, B, C. At each area, there is a camera. After entering, if the person moves to any of these areas, the camera of that particular area recognizes the face, matches with the faces in database and updates the location of person. 

Project Objectives

Execution Plan of Project:

The execution plan of our project will contain following details:

1. Work on Face Detection Model:

Firstly, we will use a Face Detection model so that it will detect the faces through the camera. After that we will extract our region of interest (ROI) which will be our data from the whole picture.

1. Maintain Dataset:

Secondly, we will maint­ain our dataset means the images we have extracted from the video recording of camera. We will extract multiple images of a face, which is detected by the model. These images will be our dataset and it will be maintained in the database.

1. Work on Face Recognition Model:

After that, we will work on the Face Recognition to recognize the face through camera. After that we will recognize the face on basis of the dataset we have maintained. If a new face is detected, a system generated id will be allocated to that face and its dataset will be maintained in the database.

1. Work on Location Monitoring:

We will have cameras on different locations. If a person is at location A, the camera at location A, will recognize the face and his location will be stored. When he moves to location B, camera at location B will recognize the face and his location will automatically be updated. In addition, we will update the timestamp as the person is recognized in a new location.

1. Location History Of Person:

All the movement record of a person is maintained on daily basis, which locations the person has visited on a day.

Project Implementation Method

The method of face detection in pictures is complicated because of variability present across human faces such as pose, expression, position and orientation, skin colour, the presence of glasses or facial hair, differences in camera gain, lighting conditions, and image resolution.

In recent times, a lot of study work proposed in the field of Face Recognition and Face Detection to make it more advanced and accurate, but it makes a revolution in this field when Viola-Jones comes with its Real-Time Face Detector, which is capable of detecting the faces in real-time with high accuracy.

There are many methods for face detection available nowadays.

1. Opencv Haar Cascades method
2. Opencv dnn method
3. Dlib Hog method
4. Dlib dnn method
5. Face Recognition module (built on dlib).

Facial recognition is a technology used for identifying or verifying a person from an image or a video. There are various methods by which facial recognition systems work, but in general, they work by comparing selected facial features from a given image with faces within a database.

Face recognition is really a series of several related problems:

1. First, look at a picture and find all the faces in it
2. Second, focus on each face and be able to understand that even if a face is turned in a weird direction or in bad lighting, it is still the same person.
3. Third, be able to pick out unique features of the face that you can use to tell it apart from other people— like how big the eyes are, how long the face is, etc.
4. Finally, compare the unique features of that face to all the people you already know to determine the person’s name.

For recognition there are different algorithms and methods including Local binary pattern histogram method, Eigen Faces method, Fisherfaces method, PCA and SVM, CNN based methods and so on.

We will be using Face Recognition module of python in our case, which not only detects but also provide functionality to recognize faces.

Face Recognition:

Recognize and manipulate faces from Python or from the command line with the world's simplest face recognition library.

Built using dlib's state-of-the-art face recognition built with deep learning. The model has an accuracy of 99.38% on the Labeled Faces in the Wild benchmark.

Benefits of the Project Face Recognition is very hot nowadays and it has a wide range of applications. Our location tracking system can benefit in following areas.

• Prevent Crimes:

Face recognition is currently being used to instantly identify when known shoplifters, organized retail criminals or people with a history of fraud enter retail establishments. Photographs of individuals can be matched against large databases of criminals so that loss prevention and retail security professionals can be instantly notified when a shopper enters a store that prevents a threat.

• Find Missing Ones:

Face recognition can be used to find missing children and victims of human trafficking. As long as missing individuals are added to a database, law enforcement can become alerted as soon as they are recognized by face recognition—be it an airport, retail store or other public space.

• Help Law Enforcement:

The Face Recognition system can help police officers to check the person’s record they are dealing with using their mobile app, making them aware of what kind of person they are dealing with and if they take security steps early.

Technical Details of Final Deliverable

Finally we will be making a web aplication where we will show the details of people detected with respect to system generated ids. Also we will plot theitr locations in which areas they move and at what time.

Final Deliverable of the Project Software SystemCore Industry SecurityOther Industries Education Core Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	63600
Nvidia gtx 750 ti	Equipment	1	20000	20000
a4tech web camera 1080p	Equipment	1	3600	3600
PC upgrade xeon e5 1650v2	Equipment	1	40000	40000