La traduction de cette page n'est pas à jour. Cliquez ici pour voir la dernière version en anglais.

Détection et extraction des caractéristiques

Recalage d’images, détection des points d’intérêt, extraction des descripteurs de caractéristiques, mise en correspondance de points d’intérêt et recherche d’images

Les caractéristiques locales et leurs descripteurs sont les blocs de base d’un grand nombre d’algorithmes de Computer Vision. Leurs applications comprennent le recalage d’images, la détection et la classification d’objets, le pistage, l’estimation du mouvement et la recherche d’image par le contenu (CBIR). Ces algorithmes utilisent les caractéristiques locales pour mieux gérer les changements d’échelle, la rotation et l’occlusion. Les algorithmes de Computer Vision Toolbox™ comprennent les détecteurs de coins FAST, Harris et Shi & Tomasi ainsi que les détecteurs de blobs SIFT, SURF, KAZE et MSER. La toolbox inclut les descripteurs SIFT, SURF, FREAK, BRISK, LBP, ORB et HOG. Vous pouvez associer plusieurs détecteurs et descripteurs en fonction des exigences de votre application.

Fonctions

développer tout

Détecter des caractéristiques

`detectBRISKFeatures`	Detect BRISK features
`detectFASTFeatures`	Detect corners using FAST algorithm
`detectHarrisFeatures`	Detect corners using Harris–Stephens algorithm
`detectKAZEFeatures`	Detect KAZE features
`detectMinEigenFeatures`	Detect corners using minimum eigenvalue algorithm
`detectMSERFeatures`	Detect MSER features
`detectORBFeatures`	Detect ORB keypoints
`detectSIFTFeatures`	Detect scale invariant feature transform (SIFT) features (depuis R2021b)
`detectSURFFeatures`	Detect SURF features

Extraire des caractéristiques

`extractFeatures`	Extract interest point descriptors
`extractLBPFeatures`	Extract local binary pattern (LBP) features
`extractHOGFeatures`	Extract histogram of oriented gradients (HOG) features

Faire correspondre des caractéristiques

`matchFeatures`	Find matching features
`matchFeaturesInRadius`	Find matching features within specified radius (depuis R2021a)

Recherche d’image

`imwarp`	Apply geometric transformation to image
`estgeotform2d`	Estimate 2-D geometric transformation from matching point pairs (depuis R2022b)
`estgeotform3d`	Estimate 3-D geometric transformation from matching point pairs (depuis R2022b)
`vision.AlphaBlender`	(Not recommended) Combine images, overlay images, or highlight selected pixels
`vision.BlockMatcher`	Estimate motion between images or video frames
`vision.LocalMaximaFinder`	(Removed) Find local maxima in matrices
`vision.TemplateMatcher`	Locate template in image

Visualisation et affichage

`insertMarker`	Insert markers in image or video
`insertShape`	Insert shapes in image or video
`showMatchedFeatures`	Display corresponding feature points
`showShape`	Display shapes on image, video, or point cloud (depuis R2020b)
`insertObjectAnnotation`	Annotate truecolor or grayscale image or video
`insertObjectKeypoints`	Insert object keypoints in image (depuis R2023b)
`insertText`	Insert text in image or video
`imshow`	Display image
`imshowpair`	Compare differences between images
`vision.GammaCorrector`	(To be removed) Apply or remove gamma correction from images or video streams
`vision.ChromaResampler`	Downsample or upsample chrominance components of images

Stocker des caractéristiques

`binaryFeatures`	Object for storing binary feature vectors
`BRISKPoints`	Object for storing BRISK interest points
`cornerPoints`	Object for storing corner points
`KAZEPoints`	Object for storing KAZE interest points
`MSERRegions`	Object for storing MSER regions
`ORBPoints`	Object for storing ORB keypoints
`SIFTPoints`	Object for storing SIFT interest points (depuis R2021b)
`SURFPoints`	Object for storing SURF interest points

Transformer des objets

`rigidtform2d`	2-D rigid geometric transformation (depuis R2022b)
`simtform2d`	2-D similarity geometric transformation (depuis R2022b)
`affinetform2d`	2-D affine geometric transformation (depuis R2022b)
`projtform2d`	2-D projective geometric transformation (depuis R2022b)
`rigidtform3d`	3-D rigid geometric transformation (depuis R2022b)
`simtform3d`	3-D similarity geometric transformation (depuis R2022b)

Rechercher des images

Créer une base de données de reconnaissance

`bagOfFeatures`	Bag of visual words object
`invertedImageIndex`	Search index that maps visual words to images

Rechercher des images

`retrieveImages`	Search image set for similar image
`imageDatastore`	Datastore for image data
`evaluateImageRetrieval`	Evaluate image search results

Rubriques

Local Feature Detection and Extraction
Learn the benefits and applications of local feature detection and extraction.
Point Feature Types
Choose functions that return and accept points objects for several types of features.
Systèmes de coordonnées
Définir les indices des pixels, les coordonnées spatiales, et les systèmes de coordonnées 3D
Draw Shapes and Lines
When you specify the type of shape to draw, you must also specify its location on the image.
Image Retrieval with Bag of Visual Words
Retrieve images from a collection of images similar to a query image using a content-based image retrieval (CBIR) system.

Exemples présentés

Image Retrieval Using Customized Bag of Features

Create a Content Based Image Retrieval (CBIR) system using a customized bag-of-features workflow.

Ouvrir le live script

Pattern Matching

Use the 2-D normalized cross-correlation for pattern matching and target tracking. The example uses predefined or user specified target and number of similar targets to be tracked. The normalized cross correlation plot shows that when the value exceeds the set threshold, the target is identified.

Ouvrir le script

Find Object in Cluttered Scene Using Image Point Features

Detect a particular object in a cluttered scene, given a reference image of the object.

Ouvrir le script

Digit Classification Using HOG Features

Classify digits using HOG features and a multiclass SVM classifier.

Ouvrir le live script

Automatically Find Image Rotation and Scale

Demonstrates how to automatically determine the geometric transformation between two images. Specifically, when one image is distorted in relation to another due to rotation and scaling, the functions detectSURFFeatures and estimateGeometricTransform2D can be employed to identify the rotation angle and scale factor. Subsequently, these parameters can be used to transform the distorted image back to its original appearance.

Ouvrir le script

Create Panorama

Automatically stitch multiple images into panorama. The procedure for image stitching is an extension of feature based image registration. Instead of registering a single pair of images, multiple image pairs are successively registered relative to each other to form a panorama.

Ouvrir le live script

Stabilize Video Using Image Point Features

Stabilize a video that was captured from a jittery platform. One way to stabilize a video is to track a salient feature in the image and use this as an anchor point to cancel out all perturbations relative to it. This procedure, however, must be bootstrapped with knowledge of where such a salient feature lies in the first video frame. In this example, we explore a method of video stabilization that works without any such a priori knowledge. It instead automatically searches for the "background plane" in a video sequence, and uses the observed distortion to correct for camera motion.

Ouvrir le live script

Object Counting

Use morphological operations to count objects in a video stream.

Ouvrir le live script

Cell Counting

Use a combination of basic morphological operators and blob analysis to extract information from a video stream. In this case, the example counts the number of E. Coli bacteria in each video frame. Note that the cells are of varying brightness, which makes the task of segmentation more challenging.

Ouvrir le live script