Abstract | ||
---|---|---|
This paper proposes a novel facial expression recognition system based on image features. There are two main processes in the proposed system, which are face detection and facial expression recognition (FER). The face detection process uses Haar-like features, and the region of interest is reset to reduce the variable of appearance changes. The FER process extracts histogram of oriented gradients (HOG) features from each facial region, and then, support vector machine is performed to classify the final facial expression. In the experimental results, the system exactly recognized the facial expression of a certain person, and the proposed system had the F-1 score of 0.8759. |
Year | Venue | Keywords |
---|---|---|
2017 | PROCEEDINGS INTERNATIONAL SOC DESIGN CONFERENCE 2017 (ISOCC 2017) | machine learning, supervised learning, facial expression recognition |
Field | DocType | ISSN |
Facial recognition system,Pattern recognition,Computer science,Feature (computer vision),Support vector machine,Real-time computing,Feature extraction,Facial expression,Histogram of oriented gradients,Artificial intelligence,Region of interest,Face detection | Conference | 2163-9612 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sanghyuk Kim | 1 | 0 | 0.34 |
Gwon Hwan An | 2 | 2 | 1.71 |
Suk-Ju Kang | 3 | 127 | 27.68 |