Emotion Detection from Facial Expression Using Different Feature Descriptor Methods with Convolutional Neural Networks

Fatih ALTEKİN; Hasan DEMİR

doi:https://doi.org/10.55581/ejeas.857761

Article Details

Emotion Detection from Facial Expression Using Different Feature Descriptor Methods with Convolutional Neural Networks

Authors:

Fatih ALTEKİN | Hasan DEMİR

Publisher:

Tekirdag Namik Kemal University

Main Topics:

Applied physics

Journal:

European Journal of Engineering and Applied Sciences 2021 Vol.4 Issue 1, pp.14-17

Document Type:

Article

Publication Date:

7/2021

Document Language:

English

Document ID (Org No.):

2000424752

eISSN:

2667-8454

pISSN:

2651-3412

DOI:

https://doi.org/10.55581/ejeas.857761

Abstract:

 

In this article, image processing techniques to detect facial emotion expressions are examined. Studies done to detect facial expression are given in stages. The success of the convolutional neural networks (CNN) method in emotional expression has been investigated. A set of 981 CK + pictures containing human faces in 7 emotion categories was used. The success rates when using HOG, LBP, Wavelet feature of images and the original state of the images in the data set were compared.

 


Bu makalede, yüzdeki duygu ifadelerini tespit etmek için imge işleme teknikleri incelenmiştir. Yüzdeki duygu ifadelerini tespit etmek için yapılan çalışmalar aşamalar halinde verilmiştir. Evrişimsel sinir ağları (CNN) yönteminin duygu ifadeleri tespitindeki başarısı ele alınmıştır. 7 duygu katogorisinde, insan yüzleri içeren 981adet imgeden oluşan CK+ imge seti kullanılmıştır. Veri setindeki imgelerin orijinal hali ve HOG, LBP ve İmgelerin dalgacık dönüşümü özniteliklerinin kullanıldığı durumlardaki başarı oranları karşılaştırılmıştır.

.

Article Details

Emotion Detection from Facial Expression Using Different Feature Descriptor Methods with Convolutional Neural Networks

Authors: Fatih ALTEKİN | Hasan DEMİR

Publisher: Tekirdag Namik Kemal University

Main Topics: Applied physics

Journal: European Journal of Engineering and Applied Sciences 2021 Vol.4 Issue 1, pp.14-17

Document Type: Article

Publication Date: 7/2021

Document Language: English

Document ID (Org No.): 2000424752

eISSN: 2667-8454

pISSN: 2651-3412

DOI: https://doi.org/10.55581/ejeas.857761

Issues

Authors:

Fatih ALTEKİN | Hasan DEMİR

Publisher:

Tekirdag Namik Kemal University

Main Topics:

Applied physics

Journal:

European Journal of Engineering and Applied Sciences 2021 Vol.4 Issue 1, pp.14-17

Document Type:

Article

Publication Date:

7/2021

Document Language:

English

Document ID (Org No.):

2000424752

eISSN:

2667-8454

pISSN:

2651-3412

DOI:

https://doi.org/10.55581/ejeas.857761