AI engineering glossary · Computer vision
What is SIFT?
SIFT: Scale-Invariant Feature Transform, a classic algorithm that detects keypoints at several scales and describes them with 128-number vectors of local gradient orientations. It matches the same object across different sizes, angles and lighting.
SIFT: an example
SIFT can match a photo of a monument taken from far away with a close-up of the same monument.
Related terms
More Computer vision terms
- Single-stage detector
- Sobel operator
- Stride
- Text detection
- Text recognition
- Thresholding
- Top-k accuracy
- Translation invariance
Where you learn it
SIFT is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.