Emotion AI: Facial Key-points Detection with Deep Learning (Residual Convolutional Neural Network)

Blog

Medium Blog

Introduction

In this project, we will build, train and test a Convolutional Neural Networks with Residual Blocks to predict facial key point coordinates from facial images. This can be used as a building block in several applications, such as:

• Tracking faces in images and video
• Analyzing facial expressions
• Detecting dysmorphic facial signs for medical diagnosis
• Biometrics / face recognition

Exploratory Data Analysis

Modeling

Model Architect

Model Evaluation

Reference

Ahmed, R. (n.d.). Emotion AI: Facial key-points detection [MOOC]. Coursera. https://www.coursera.org/projects/facial-key-point-detection.

Somers, M. (2019, March 8). Emotion AI explained. MIT Sloan. Retrieved September 11, 2021, from https://mitsloan.mit.edu/ideas-made-to-matter/emotion-ai-explained.