AI engineering glossary · Computer vision
What is NMS (non-maximum suppression)?
Non-maximum suppression (also called NMS): A post-processing step that removes duplicate detections of the same object: keep the highest-scoring box, discard other boxes that overlap it by more than an IoU threshold, and repeat. It leaves one box per object.
Non-maximum suppression: an example
Five boxes cluster around one face; with threshold 0.5, NMS keeps the highest-confidence one and drops the rest.
Related terms
More Computer vision terms
- Object detection
- OpenCV
- Optical character recognition
- ORB
- Otsu's method
- Padding
- Panoptic segmentation
- Patch embedding
Where you learn it
Non-maximum suppression is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.