Feature Detection

Using a variety of state-of-the-art methods, the Wolfram Language provides immediate functions for detecting and extracting features in images and other arrays of data. The Wolfram Language supports specific geometrical features such as edges and corners, as well as general keypoints that can be used to register and compare images.

TextRecognize extract characters from an image

BarcodeRecognize extract the barcode from an image

FindFaces find human faces in an image

Points-of-Interest Detection

ImageKeypoints find keypoints and associated feature vectors in an image

ImageCorners find corners

CornerFilter compute a measure for the presence of a corner

Contour Detection

FindImageShapes detect shapes (lines, circles, ellipses) in an image

EdgeDetect detect edges in an image using Canny and other methods

CrossingDetect, ContourDetect detect zeros and zero crossings

ImageLines find Hough lines in an image

ImageMesh convert an image foreground to a mesh region

GradientFilter  ▪  LaplacianGaussianFilter  ▪  ImageFilter  ▪  ImageConvolve

Extrema Detection

MinDetect, MaxDetect detect regional and extended minima and maxima

PeakDetect, FindPeaks find the positions of peaks

Foreground/Background Separation

EstimatedBackground estimate a smooth background

RemoveBackground compute and remove the background of an image

Feature Tracking

ImageCorrespondingPoints find corresponding keypoints in pairs of images

ImageDisplacements find the optical flow across a sequence of images

ImageFeatureTrack track features across a sequence of images

Image Transforms

Radon, InverseRadon Radon and inverse Radon transforms

ImagePeriodogram squared magnitude of the Fourier transform