Image Preprocessing

Resizing, normalization and data augmentation.

20 minutesComputer vision

What you will learn

  • Listing the preprocessing steps
  • Understanding the benefit of augmentation

Common steps: resizing to one size, normalizing the values to [0,1], converting to grayscale when colour does not matter, and data augmentation (Augmentation: flipping, rotation, changing lighting) to diversify training.

Transfer learning requires the size and normalization the original network was trained with, and the visual tools do this automatically.

Implementation steps with the tool

  1. Teachable Machine: photograph the objects from different angles and in different lighting (manual data augmentation).

Quick review question

Why might flipping an image horizontally do harm when recognising letters?

Tools