Real-time face detection and recognition system in complex backgrounds.

摘要

This thesis provides a fast and reliable system for real-time face detection and recognition in complex backgrounds. Most current face recognition systems identify faces under constrained conditions, such as constant lighting condition, the same background. In the real world, people need to be recognized in complex backgrounds under different conditions, such as tilted head poses, various facial expressions, dark or strong lighting conditions. Meanwhile, because of large amounts of real-time applications for face recognition, such as intelligent robot, unmanned vehicle, security monitor, fast face detection rate and recognition rate need to be satisfied for the real-time requirement. In this project, a fast and reliable system is designed to real-time detect and recognize faces under various conditions. Frames are obtained directly from VGA camera. Image pre-processing and face detection, collection, recognition are sequentially implemented on the frames.;Local binary pattern and Haar-like feature are used for face detection and two eyes detection. Local binary pattern encodes every pixel of the image for texture extraction, which is several times faster than Haar-like feature detection. Haar-like feature uses intensity difference of neighboring rectangular regions to match facial feature. Thousands of Haar-like features are applied to descript local primitives for accurate detection. Adaptive boosting algorithm is used for selecting the best weak classifiers and combine these best weak classifiers together into a strong classifier. Cascading method divides the strong classifier into several stages to enhance detection rate. Affine transformation is implemented to unify the size of detected facial images and align two eyes to the desired position for accurate recognition. Gaussian filter is designed to smooth facial images. Principal component analysis (PCA) is used for face recognition, which is fast to identify high-dimensional faces with few principal components.