Emotion Analysis by Deep Learning Methods using Convolutional Neural Network

  • Choudhary P
  • Vijay S
Citations of this article
Mendeley users who have this article in their library.


In machine learning, CNN uses a variation of multilayer perceptron designed to use relatively little pre-processing compared to other image classification algorithms. This means that the network learns the filtering that was hand-engineered in other algorithms. This independence of human endeavors for feature design is a major advantage due to which it is used in this paper. In the context of machine vision, image recognition is the capability of software to identify objects in images. The algorithm is used to train the model from a data set of around 10000 images and 12 videos. The model will detect and recognize types of feelings through the person's expression, such as anger, fear, happiness, sadness, and surprise. The model gives an accuracy of 67%. This provides a behavioral measure for the study of emotion, cognitive process and social interaction.




Choudhary, P., & Vijay, S. (2019). Emotion Analysis by Deep Learning Methods using Convolutional Neural Network. International Journal of Engineering and Advanced Technology (IJEAT), (4), 2249–8958.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free