An Accurate Facial Expression Detector using Multi-Landmarks Selection and Local Transform Features
- Title
- An Accurate Facial Expression Detector using Multi-Landmarks Selection and Local Transform Features
- Author
- 김기범
- Keywords
- Face detectionlandmark analysisSVM classifierfacial expressions recognition
- Issue Date
- 2020-04
- Publisher
- IEEE
- Citation
- 2020 3rd International Conference on Advancements in Computational Sciences (ICACS), Page. 1-6
- Abstract
- In the past few years, facial features detection and landmarks analysis plays a vital role in several practical application such as surveillance system, crime detector and age estimation. In this paper, we proposed a novel approach of recognizing facial expressions based on multi landmark detectors, local transform features and recognizer classifier. The proposed system is divided into four stages. (a) Face detection using skin color segmentation and ellipse fitting, (b) Plotting landmarks on facial features, (c) Feature extraction using euclidean distance, HOG and LBP. While, (d) SVM classification learner is used to classify six basic facial expressions like Neutral, Happy, Sad, Anger, Disgust, and Surprise. The proposed method is applied on two facial expression datasets i-e. MMI facial expressions dataset and Chicago Face dataset and achieved accuracy rates of 80.8% and 83.01%, respectively. The proposed system outperforms the state-of-the-art facial expression recognition system in terms of recognition accuracy. The proposed system should be applicable to different consumer application domains such as online business negotiations, consumer behavior analysis, E-learning environments, and virtual reality practices.
- URI
- https://ieeexplore.ieee.org/document/9055954?arnumber=9055954&SID=EBSCO:edseeehttps://repository.hanyang.ac.kr/handle/20.500.11754/179208
- DOI
- 10.1109/ICACS47775.2020.9055954
- Appears in Collections:
- COLLEGE OF COMPUTING[E](소프트웨어융합대학) > MEDIA, CULTURE, AND DESIGN TECHNOLOGY(ICT융합학부) > Articles
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML