Real-time facial expression recognition system (FERS)
Real-Time Facial Expression Recognition System (FERS) is developed to recognize facial expressions.Findings claiming that humans display their emotions most expressively through face expressions and body gestures. Humans are more likely to consider computers to be human like when those computers und...
Saved in:
| Main Author: | |
|---|---|
| Format: | Undergraduates Project Papers |
| Language: | English |
| Published: |
2011
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/4334/1/THELEHAESWARY_APPALASAMY.PDF http://umpir.ump.edu.my/id/eprint/4334/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Malaysia Pahang |
| Language: | English |
| Summary: | Real-Time Facial Expression Recognition System (FERS) is developed to recognize facial expressions.Findings claiming that humans display their emotions most expressively through face expressions and body gestures. Humans are more likely to consider computers to be human like when those computers understand and display appropriate nonverbal communicative behaviour.So,the interaction between humans and computers will be-more natural if computers are able to understand the nonverbal behaviour of their 'human counterparts and recognize their affective state. Therefore,this project is carried out to build a prototype to recognize facial expressions. Evolutionary methodology was implemented in this system design by using several image processing techniques include imageacquisition,image enhancement (or known as pre-processing stages)and feature extraction.Hundred and fifty four sample,data of human faces in the range of 18 to 26 years old is tested.The system first applies some pre-processing stages to enhance the input image and reduce the noise.The face boundary will then be detected. The region of interest(i.e. mouth and eyes)will be determined,from which,features will be extracted. Finally, the face'will be -classified into-one of three different classes using the Kmeans method based on the features extracted.The method was applied and tested on a datase-of 1-54 images of faces and -the success rate obtained was 94.-80%. |
|---|