Human Emotion Detection Based On Facial Expression Using Convolution Neural Network
Penke Satyanarayana1, Pathan Madhar Khan2, Shaik Junez Riyaz3
1Penke Satyanarayana, Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Guntur, (Andhra Pradesh), India.
2Pathan Madhar Khan, Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Guntur, (Andhra Pradesh), India.
3Shaik Junez Riyaz, Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Guntur, (Andhra Pradesh), India.
Manuscript received on 23 March 2019 | Revised Manuscript received on 30 March 2019 | Manuscript published on 30 March 2019 | PP: 756-761 | Volume-7 Issue-6, March 2019 | Retrieval Number: F2823037619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Deep learning is an achievement inside the field of computer vision. This paper deals with deep learning frameworks to see outward appearances that address human feelings. Face feelings are the impressions of the inner emotions of a human. The human expressions play an essential role in nonverbal communication. Our article deals with eight standard feelings happiness, angry, sadness, fearing, surprising, disgusting, contempt and neutral. various researches have been performed, in appearing sagacious computer vision which can see the human’s tendency. The proposed work achieves improved performance model with fewer epochs. To implement this, efficient algorithms and techniques are used while generating the model. In the preprocessing methodology, Histogram equalization has been applied to the raw input images. Batch Normalization technique is used in the proposed model for better learning rate. CK+ dataset is used for training and testing the model. To test the model in real time harr feature-based cascade classifier is used for detecting the face. the model was trained on Google Colab with a GPU.
Keywords: Batch Normalization, Convolution Neural Network, Emotion Detection, Histogram equalization.
Scope of the Article: Advanced Computer Networking