Feature Detection and Extraction

Interest point detection, extracting feature descriptors, and point feature matching

Local features and their descriptors are the building blocks of many computer vision algorithms. Their applications include image registration, object detection and classification, tracking, and motion estimation. Using local features enables these algorithms to better handle scale changes, rotation, and occlusion. The Computer Vision System Toolbox™ provides the FAST, Harris, and Shi & Tomasi corner detectors, and the SURF and MSER blob detectors. The toolbox includes the SURF, FREAK, BRISK, and HOG descriptors. The detectors and the descriptors can be mixed and matched depending on the requirements of your application.


detectBRISKFeatures Detect BRISK features and return BRISKPoints object
detectFASTFeatures Detect corners using FAST algorithm and return cornerPoints object
detectHarrisFeatures Detect corners using Harris–Stephens algorithm and return cornerPoints object
detectMinEigenFeatures Detect corners using minimum eigenvalue algorithm and return cornerPoints object
detectMSERFeatures Detect MSER features and return MSERRegions object
detectSURFFeatures Detect SURF features and return SURFPoints object
extractFeatures Extract interest point descriptors
extractHOGFeatures Extract histogram of oriented gradients (HOG) features
matchFeatures Find matching features
showMatchedFeatures Display corresponding feature points


binaryFeatures Object for storing binary feature vectors
BRISKPoints Object for storing BRISK interest points
cornerPoints Object for storing corner points
SURFPoints Object for storing SURF interest points
MSERRegions Object for storing MSER regions

System Objects

vision.BoundaryTracer Trace object boundary
vision.EdgeDetector Find object edge


Corner Detection Calculate corner metric matrix and find corners in images
Edge Detection Find edges of objects in images using Sobel, Prewitt, Roberts, or Canny method
Template Matching Locate a template in an image
Trace Boundary Trace object boundaries in binary images
Was this topic helpful?