Computer Vision System Toolbox™ provides pretrained object detections and the functionality to train a custom detector. The cascade object detector uses the Viola-Jones algorithm to detect people's faces, noses, eyes, mouth, or upper body. The people detector detects people in an input image using the histogram of oriented gradients (HOG) features and a trained support vector machine (SVM) classifier.
You can customize the cascade object detector using the
trainCascadeObjectDetector function . You can also use
the Image Labeler, feature extractors, and the Statistics and Machine Learning Toolbox™ classifiers to create a custom detector.
|Image Labeler||Label ground truth in a collection of images|
|Detect objects using aggregate channel features|
|Detect people using aggregate channel features|
|Detect objects using Faster R-CNN deep learning detector|
|Detect objects using Fast R-CNN deep learning detector|
|Detect objects using R-CNN deep learning detector|
|Detect objects using the Viola-Jones algorithm|
|Foreground detection using Gaussian mixture models|
|Detect upright people using HOG features|
|Properties of connected regions|
|Train ACF object detector|
|Train cascade object detector model|
|Train a Fast R-CNN deep learning object detector|
|Train a Faster R-CNN deep learning object detector|
|Train an image category classifier|
|Train an R-CNN deep learning object detector|
|Detect BRISK features and return BRISKPoints object|
|Detect corners using FAST algorithm and return cornerPoints object|
|Detect corners using Harris–Stephens algorithm and return cornerPoints object|
|Detect KAZE features|
|Detect corners using minimum eigenvalue algorithm and return cornerPoints object|
|Detect MSER features and return MSERRegions object|
|Detect SURF features and return SURFPoints object|
|Extract interest point descriptors|
|Find matching features|
|Evaluate miss rate metric for object detection|
|Evaluate precision metric for object detection|
|Convert rectangle to corner points list|
|Compute bounding box overlap ratio|
|Select strongest bounding boxes from overlapping clusters|
Train a custom classifier
Interactively label rectangular ROIs for object detection, pixels for semantic segmentation, and scenes for image classification.
Retrieve images from a collection of images similar to a query image using a content-based image retrieval (CBIR) system.
Use the Computer Vision System Toolbox™ functions for image category classification by creating a bag of visual words.
This example shows how to classify digits using HOG features and a multiclass SVM classifier.
This example shows how to use a bag of features approach for image category classification.
This example shows how to create a Content Based Image Retrieval (CBIR) system using a customized bag-of-features workflow.
Learn the benefits and applications of local feature detection and extraction
Choose functions that return and accept points objects for several types of features
Specify pixel Indices, spatial coordinates, and 3-D coordinate systems
This example shows how to detect a particular object in a cluttered scene, given a reference image of the object.
This example shows how to use the 2-D normalized cross-correlation for pattern matching and target tracking.