A Study of Facial Expression Recognition by Hybrid Technique

Abstract: This study gives the knowledge about facial expression recognition by using hybrid technique. Hybrid technique is nothing but unifying two techniques to increase the recognition rate. Human expressions are fundamentally categorized by six classes, such as happy, neutral, sad, anger, surprise, and disgust. The implementation includes for finding facial expressions are local binary pattern used for face recognition and Haar-cascade classifier for face detection. Joint and transfer learning approaches will produce best outcomes and it will further increase the results. In this paper two techniques are used local binary pattern and local binary pattern histogram with haar cascade classifier. By using these techniques it will detect the facial expression and as well as it will differentiate the recognition rate between LBP and LBPH. This paper will notify the recognition rate of the respective image and it will also show the time taken for training the image. If we employ single technique the recognition rate will be low similarly if we combine two techniques then the recognition rate will be high. Face expression recognition is most effective and these are used in many real time applications by many apps for security purposes.

Keywords: Hybrid technique, facial expression recognition, feature extraction, face detection, face recognition, local binary pattern, haar-cascade classifier, local binary pattern histogram.