Facial expressions provide an important channel of nonverbal communication. Facial recognition techniques detect people's emotions using their facial expressions and have found applications in technical fields such as Human-Computer-Interaction (HCI) and security monitoring. Technical applications generally require fast processing and decision making. Therefore, it is imperative to develop innovative recognition methods that can detect facial expressions effectively and efficiently.Traditionally, human facial expressions are recognized using standard images. Existing methods of recognition require subjective expertise and high computational costs. This thesis proposes a novel method for facial expression recognition using image edge detection based on Bi-dimensional Empirical Mode Decomposition (BEMD). In this research, a BEMD based edge detection algorithm was developed, a facial expression measurement metric was created, and an intensive database testing was conducted. The success rates of recognition suggest that the proposed method could be a potential alternative to traditional methods for human facial expression recognition with substantially lower computational costs. Furthermore, a possible blind-detection technique was proposed as a result of this research. Initial detection results suggest great potential of the proposed method for blind-detection that may lead to even more efficient techniques for facial expression recognition.
展开▼
