AI engineering glossary · Computer vision
What is feature matching?
Feature matching: Pairing keypoints from two images by finding descriptors that are closest to each other, often with a ratio test to reject ambiguous pairs. The matches feed tasks like stitching, 3D reconstruction and object recognition.
Feature matching: an example
With Lowe's ratio test at 0.75, a match is kept only if the best distance is under 75% of the second-best distance.
Related terms
More Computer vision terms
- Feature pyramid network
- Fine-tuning
- Fully convolutional network
- Gaussian blur
- Global average pooling
- Grad-CAM
- Grayscale image
- Histogram equalisation
Where you learn it
Feature matching is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.