Open Access Open Access  Restricted Access Subscription or Fee Access

Facial Expression Recognition using Convolutional Neural Network

Hamsavahan H, Lohit S., Nandakishore T. J., Kalaiselvan V

Abstract


Machine learning is a subset of Artificial intelligence. Machine learning enables self-learning from past data and predicts the future. Machine learning is used in many applications such as self-driving cars, Google translate etc. Deep learning is a subset of machine learning. CNN is a convolutional neural network. The CNN approach is very effective in image classification. The target of this exploration is to assist a look acknowledgment framework dependent on convolutional neural organization. The conventional CNN network module is used to extract primary expressional vector (EV). The expressional vector (EV) is generated by tracking down relevant facial points of importance.In the proposed solution, gray scale image in Kaggle. This methodology empowers to order seven fundamental feelings which comprise of furious, disdain, dread, glad, unbiased, dismal and shock from Kaggle dataset. TensorFlow framework is used in facial expression with the accuracy of 92%.


Keywords


Facial expression, CNN, Machine Learning, Conv2D, expressional vector

Full Text:

PDF

Refbacks

  • There are currently no refbacks.