This path focuses on teaching you how to build systems that can interpret and understand visual information from the world, such as images and video.

Who it’s for:

Aspiring engineers who want to work on AI applications like facial recognition, medical imaging, self-driving cars, and more.

What you’ll learn:

• Image processing fundamentals with OpenCV

• Working with image datasets and annotations

• Convolutional Neural Networks (CNNs) using TensorFlow or PyTorch

• Object detection, image classification, and segmentation

• Data augmentation and transfer learning

• Deployment of vision models (e.g., as APIs or mobile-ready models)

• Intro to real-time inference and edge deployment (lightweight)

What you’ll build:

• Projects such as:

  • Facial expression classifier

  • Traffic sign detector

  • Medical image anomaly detection

• End-to-end pipeline from dataset to deployment