Skip to course content
Free computer vision course

Computer Vision and Multimodal AI

Module 04 Summary

What this module established

Edges are gradients: a shadow and a printed line produce them exactly as an object boundary does. Contours find connected regions, not objects - touching objects merge, and the information needed to split them is not in the mask.

Carry forward

Before moving on

Move on when you have answered honestly whether your target has a consistent describable appearance, with IoU, precision and recall against hand-drawn masks.