AI engineering glossary · Computer vision
What is HOG (histogram of oriented gradients)?
Histogram of oriented gradients (also called HOG): A hand-designed feature that divides an image into small cells and records a histogram of gradient directions in each, normalised over larger blocks. It captures shape and was the basis of classic pedestrian detectors paired with a linear SVM.
Histogram of oriented gradients: an example
A 64 x 128 pedestrian window produces a feature vector of 3,780 numbers with the standard HOG settings.
Related terms
More Computer vision terms
- Homography
- Horizontal flip
- HSV colour space
- Image classification
- Image embedding
- Image gradient
- Image histogram
- Image normalisation
Where you learn it
Histogram of oriented gradients is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.