Face detection for a video surveillance system | |
| Author | Khin Swe Nwe |
| Call Number | AIT Thesis no.CS-07-08 |
| Subject(s) | Interactive video Fetal monitoring |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Computer Science, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis ; no. CS-07-08 |
| Abstract | Security is one of the most persistent problems in an organization. Like others, our Computer Science laboratory under School of Engineering and Technology (SET), Asian Institute of Technology (AIT), has setup an access control system for the security of laboratories facilities. Although security camera is currently used for taking the pictures and access control system is used to enter the laboratory, these two systems are not connected each other. From the security point of view, using the face detection system is one of the best ways to solve the current insecure problem. This study proposed a user¬friendly system based on analysis and detection of frontal or profile images of the face when someone enters the room by tracking the person from the images captured by the web camera that I set up on Fedora Core 5.0 to provide a solution to the security problem. In this thesis, it can be viewed as two systems (a) face detection system and (b) run-time information system. Deploying a face detection system could make it easy for administrators to check and track the face of the person who enters to the laboratory. After the face detection step, I store the images getting from face detection in MySQL database and then show the result as three reports on the web application interface written in the PHP programming language. So, this study attempts to design and implement a security information system employing image-based face detection. The results of the approaches are evaluated over a number of images captured by the Lab Camera. To measure the effectiveness of the approaches, the accuracies of the face detection system are also evaluated by end-users based on the simplification and ease of use of the features, and functionality and flexibility of the system. |
| Year | 2007 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. CS-07-08 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Dailey, Matthew N.; |
| Examination Committee(s) | Guha, Sumanta;Janecek, Paul; |
| Scholarship Donor(s) | Prospect Burma;Asian Institute of Technology Fellowship; |
| Degree | Thesis (M.Sc.) - Asian Institute of Technology, 2007 |