.png){kind=icon}
.png){kind=icon}
Return
Facial expression identification using gradient local phase
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-018-7069-z.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper presents an automatic facial expression recognition (FER) system. The method proposed is based on an adapted gradient local phase quantization (LPQ) descriptor. Two methods for the quantization of the local phase are proposed here to improve the conventional LPQ. These methods are the phase thresholding and the phase LTP coding. An experimental study of these methods is performed for identification of both the six and seven basic expressions: happy, surprised, fear, disgust, sad, anger and neutral state. The FER system consists of three main stages. The first step consists of the detection of the face, selection of a region of interest, and normalization of this region. Then extraction of features is done by the adapted gradient LPQ method. The third step is the classification of the emotional states. The SVM are used for this purpose. Evaluation of the system performance is done on the well-known JAFFE, and Cohn and Kanade, databases, with both six and seven facial expressions.
Keywords:
Facial expression identification
Local phase quantization
Local ternary patterns
Support vector machines (SVM)
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3
Papers:
1.9W
Citations:
3.2W
Organization
No organization information available