| Summary: | 碩士 === 國立臺灣科技大學 === 電機工程系 === 94 === The study in biometrics field has vigorous development these years, especially in feature-based recognition field. Since the September 11 attacks, there are more and more specialists dig into biometrics field to develop a security system to guard against the horror attacks; therefore, the study in face recognition has become one popular method in biometrics researches. However, the face recognition is the not easy to reach high recognition rate even though it is the most intuitional method.
It is a good way to extract features by using Gabor filter, especially in finger print recognition and face recognition. The statistical learning theory is a hot topic these decades. The neural network has been used in many applications and has performed very well. These years, the support vector machine has showed its good classification ability and there are many papers proved that it performs better than neural network in some applications such as biometrics recognition, document classification, and data mining.
In this thesis, I built a MATLAB GUI based security platform. This platform combines Gabor feature extraction, SVM classification, and duo-threshold concepts to simulate the real-world security system. While using the SVM classifiers, I adopted one-against-rest method instead of one-against-one method because the former one has better exclusivity.
|
|---|
