Face detection approach for video surveillance
Nowadays, computer has been acts an important role in our human life. Computer has been used for purposes such as television streaming, business confidential information storage, home security monitoring, home appliances controlling and etc. All of these usages are mainly based on the computer. H...
| Main Author: | |
|---|---|
| Format: | Final Year Project Report / IMRAD |
| Language: | English English |
| Published: |
Universiti Malaysia Sarawak, UNIMAS
2010
|
| Subjects: | |
| Online Access: | http://ir.unimas.my/id/eprint/4582/ http://ir.unimas.my/id/eprint/4582/1/FACE%20DETECTION%20APPROACH%20FOR%20VIDEO%20SURVEILLANCE%20%2824pgs%29.pdf http://ir.unimas.my/id/eprint/4582/7/FACE%20DETECTION%20APPROACH%20FOR%20VIDEO%20SURVEILLANCE.pdf |
| Summary: | Nowadays, computer has been acts an important role in our human life.
Computer has been used for purposes such as television streaming, business confidential
information storage, home security monitoring, home appliances controlling and etc. All
of these usages are mainly based on the computer. Hence, our computer security system
has makes an important roles in preventing unauthorized access to the computer. Thus, a
real time face recognition system is proposed. In this report, a real time face detection
and recognition system is presented. Basically, this system applied skin colour detection
to allocate the face. The system allocates the face through skin colour sensing a nd
further focused image processing on the specific area in the image. The system
converted the facial information to grayscale image and performing face recognition
using neural network. Neural network is used for storing the facial information of the
training images. The Radial Basis Function Network is used for the particular purposes.
The system is able to detect and recognize the face trained. The system would show the
matching percentage of target with the training images. The system can perform well in
recognizing the target faces with variation of poses and facial expression with at least
60% matched the target. The system proposed a direct webcam video input in real time
based for the real time face recognition system |
|---|