Created based on deep learning - emoji - with source code

 

 An Overview of Deep Learning for Emoji

Today, we use multiple emojis or avatars to express our mood or feelings. They act as nonverbal cues for humans. They become a key part of emotion recognition, live chat, brand sentiment, product reviews, and more. Data science research on emoji-driven storytelling continues to grow.

Detecting human emotions from images is very popular, probably due to advances in computer vision and deep learning techniques. In this deep learning project, we will classify human facial expressions in order to filter and locate the corresponding emoji or avatar.

About the dataset

The image dataset we will be using for this project is FER2013 (Facial Expression Recognition 2013). It contains grayscale face images of 48*48 pixels. The images are centered and occupy the same space. The following are the categories of facial expressions present in our dataset:

  • 0: angry

  • 1: disgust

  • 2: feat

  • 3: happy

  • 4: sad

  • 5: Surprise

  • 6: Natural

Dataset: Facial Expression Recognition Dataset

Deep Learning Creates Emoji Dataset

Guess you like

Origin blog.csdn.net/tianqiquan/article/details/132385572