Classification of facial-emotion expression in the application of psychotherapy using Viola-Jones and Edge-Histogram of Oriented Gradient
- Publication Type:
- Conference Proceeding
- Citation:
- Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2016, 2016-October pp. 423 - 426
- Issue Date:
- 2016-10-13
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| 07590730.pdf | Published version | 879.9 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
© 2016 IEEE. Psychotherapy requires appropriate recognition of patient's facial-emotion expression to provide proper treatment in psychotherapy session. To address the needs this paper proposed a facial emotion recognition system using Combination of Viola-Jones detector together with a feature descriptor we term Edge-Histogram of Oriented Gradients (E-HOG). The performance of the proposed method is compared with various feature sources including the face, the eyes, the mouth, as well as both the eyes and the mouth. Seven classes of basic emotions have been successfully identified with 96.4% accuracy using Multi-class Support Vector Machine (SVM). The proposed descriptor E-HOG is much leaner to compute compared to traditional HOG as shown by a significant improvement in processing time as high as 1833.33% (p-value = 2.43E-17) with a slight reduction in accuracy of only 1.17% (p-value = 0.0016).
Please use this identifier to cite or link to this item: