Abstract:
In recent years, face recognition has attracted much attention and its research
has rapidly expanded by not only engineers but also neuroscientists since it has
many potential applications in computer vision communication and automatic
access control system. Especially, face detection is an important part of face
recognition as the first step of automatic face recognition. However, face
detection is not straightforward because it has lots of variations of image
appearance, such as pose variation (front, non-front), occlusion, image
orientation, illuminating condition and facial expression. Many novel methods
have been proposed to resolve each variation listed above. Nevertheless,
implementing the methods altogether is still a great challenge. Fortunately, the
images used in this project have some degree of uniformity thus the detection
algorithm can be simpler: first, all the faces are vertical and have a frontal view;
second, they are under almost the same illuminate condition. There is some work
done on this specific problem, but we propose an approach to detect face in realtime by machine learning which will fulfill the requirements. We have applied
some machine learning algorithms to our collected dataset’s features and got
promising results. And our model will help by detecting the face in real-time.
