| Summary: | 碩士 === 長庚大學 === 電子工程學系 === 99 === Abstract
Facial expression recognition has become a popular subject in because it is a non-verbal communication between computer and human reaction. We propose a two stage recognition algorithm. It separated into three parts, pre-processing, screening for first stage, and recognition for second stage, respectively. We use a real time object detection algorithm to extract the facial image in pre-processing. In screening part, we calculate the vectors of the images and compare with database by using Long Haar-like filters. And the last part, we extract the information from mouth for positive emotion and eyebrow for negative emotion. Finally, we use Linear Discriminant Function (LDF) to recognize the emotion by using these information. The final percentage of recognition that happy and sad are 86.21%, and angry is 75.86%.
|
|---|
