Computer Vision
Using a variety of state-of-the-art methods, the Wolfram Language provides immediate functions for image identification and object detection and recognition, as well as feature extraction. 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.
Object Detection & Recognition
ImageIdentify — identify what an image is of (out of 10,000+ objects)
ImageCases ▪ ImageContents ▪ ImagePosition ▪ ImageBoundingBoxes ▪ ImageContainsQ ▪ ImageInstanceQ
TrainImageContentDetector — train custom image object detector
Face Analysis
FindFaces — find human faces in an image
FacialFeatures ▪ FaceRecognize ▪ FaceAlign
Optical Character Recognition
TextRecognize — extract characters from an image
BarcodeRecognize ▪ FindImageText
Image Synthesis & Effects
ImageSynthesize — generate an image from a textual prompt
ImageRestyle — machine learning–based graphical style transfer
Feature Detection »
ImageGraphics — convert an image to scalable graphics
RemoveBackground — detect background from foreground and remove it
ImageKeypoints ▪ ImageCorners ▪ ImageLines ▪ ImageMesh ▪ ImageSaliencyFilter ▪ ...
Feature Tracking
ImageCorrespondingPoints — find corresponding keypoints in pairs of images
ImageFeatureTrack ▪ ImageDisplacements
Image Registration »
ImageAlign — align or register two images
ImageTransformation ▪ FindGeometricTransform ▪ ...
Machine Learning »
Classify, Predict — create and apply classifiers or predictors to images or image features
Nearest ▪ FeatureNearest ▪ FindClusters ▪ ClusteringComponents ▪ ...
Eigensystem ▪ KarhunenLoeveDecomposition ▪ ...
Image Transforms
Radon, InverseRadon — Radon and inverse Radon transforms