1 Introduction

1.1 Training & testing

1.2 Features

1. Raw pixels
2. Histograms
3. Templates
4. SIFT descriptors
   1. GIST
   2. ORB
   3. HOG….

1.2.1 General Principles of Representation

• Coverage

–Ensure that all relevant info is captured

• Concision

–Minimize number of features without sacrificing coverage

• Directness

–Ideal features are independently useful for prediction

1.3 labels