Summary: | 碩士 === 國立臺灣科技大學 === 電機工程系 === 94 === This thesis was built by using many important image processing technologies such as average filter, Sobel high-pass filter, gray-level transform, and wavelet, etc. Those technologies are basic knowledge through image processing which can be seen in many papers.
This thesis proposed a fast face detection method using active object detection, face skin color analysis, and elliptical template. This method was built by statistical learning theory which using Linear Discriminant Analysis (LDA) to separate different faces. That is, it classifies all patterns in database into new vector space by LDA algorithm. After that, the proposed method will decides whether the tester is in the same class by calculating the Euclidean distance between the tester vector and the training vectors.
|