Abstract
Abstract. Face is one of the most important communicative tools in humans’ social interactions. As a person can recognize the other’s feeling from his facial expression without saying a word. Facial expression recognition is a subject that has been aimed to develop the previous results by providing solutions through implementing and investigating the results of available algorithms in this paper. The use of averaging filter in facial expression recognition from the fixed images is a common method, however it has more errors. The other method is to use Gabor wavelets with a range of Frequencies and angles in spatial domain oriented to the input images. Although this method is highly accurate, it has time complexity and high memory usage due to the large-scale computations. In this article by segmenting the input image components into 5 parts and conflating the averaging filter with Gabor wavelets which has been derived for each segment with effective angles. In addition to the increase of previous methods’ computational speed, its accuracy has been also increased. Furthermore, designing the graphical face with the name of Robofis in Webots simulation environment indicates an imitation of those facial expressions which had been recognized by the implemented methods.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
