Feature detection is a process in computer vision that aims to find visual features within the image with particular desirable properties. Detected features can be points, image regions or continuous curves in the image. Interesting properties can include invariance to noise, perspective transformations, or properties interesting for specific usages (e.g. tracking).
Feature detection is a process in computer vision that aims to find visual features within the image with particular desirable properties.
Detected features are some subsection of the image, and can be:
- points (e.g. Harris corners)
- connected image regions (e.g. DoG or MSER regions)
- continuous curves in the image
Interesting properties can include invariance to noise, perspective transformations and viewpoint changes (camera translation and rotation), scaling (for use in visual feature matching), or properties interesting for specific usages (e.g. visual tracking).
Important information about visual features can include:
- coordinates in the image
- radius of the visual feature
- scale (octave) of the image on which the feature has been extracted
After detecting the feature with some feature detection algorithm, it is usually described by a descriptor vector (several known descriptors are used today) for the purposes of visual feature matching, while the feature's position in the image can be used directly for application in tracking.
