A Robotic Facial Expression Recognition System Using Real-Time Vision System

Abstract

The capability of recognizing human facial expression plays an important role in advanced human-robot interaction development. Through recognizing facial expressions, a robot can interact with a user in a more natural and friendly manner. In this paper, we proposed a facial expression recognition system based on an embedded image processing platform to classify different facial expressions on-line in real time. A low-cost embedded vision system has been designed and realized for robotic applications using a CMOS image sensor and digital signal processor (DSP). The current design acquires thirty 640x480 image frames per second (30 fps). The proposed emotion recognition algorithm has been successfully implemented on the real-time vision system. Experimental results on a pet robot show that the robot can interact with a person in a responding manner. The developed image processing platform is effective for accelerating the recognition speed to 25 recognitions per second with an average on-line recognition rate of 74.4% for five facial expressions.

Facial Expression Recognition Using Neural Networks and Log-Gabor Filters

“…Numerous methodologies have been proposed for facial expression analysis from both static images and image sequences [3], [4], [21], [23][24][25][26]. This study presents a computationally efficient approach to feature extraction and classification for facial expression recognition from static facial images.…”