Quantcast

Computer Vision System Toolbox

Object Detection and Recognition

Object detection and recognition are used to locate, identify, and categorize objects in images and video. Computer Vision System Toolbox provides a comprehensive suite of algorithms and tools for object detection and recognition.

Object Classification

You can detect or recognize an object in an image by training an object classifier using pattern recognition algorithms that create classifiers based on training data from different object classes. The classifier accepts image data and assigns the appropriate object or class label.

Face detection using Viola-Jones algorithm

Face detection using Viola-Jones algorithm
Using a cascade of classifiers to detect faces

Detecting people using pretrained support vector machine(SVM) with histogram of oriented gradient (HOG) features

People detector
Detecting people using pretrained support vector machine(SVM) with histogram of oriented gradient (HOG) features

Classifying digits using support vector machines (SVM) and HOG feature extraction

Digit classification
Classifying digits using support vector machines (SVM) and HOG feature extraction

Motion-Based Object Detection

Motion-based object detection algorithms use motion extraction and segmentation techniques such as optical flow and Gaussian mixture model (GMM) foreground detection to locate moving objects in a scene. Blob analysis is used to identify objects of interest by computing the blob properties from the output of a segmentation or motion extraction algorithm such as background subtraction.

Feature-Based Object Detection

Feature points are used for object detection by detecting a set of features in a reference image, extracting feature descriptors, and matching features between the reference image and an input. This method of object detection can detect reference objects despite scale and orientation changes and is robust to partial occlusions.

Reference image of object, input image; the yellow lines indicate the corresponding matched features between the two images.
Reference image of object (left), input image (right); the yellow lines indicate the corresponding matched features between the two images.

Training Object Detectors and Classifiers

Training is the process of creating an object detector or classifier to detect or recognize a specific object of interest. The training process utilizes:

  • Positive images of the object of interest at different scales and orientations
  • Negative images of backgrounds typically associated with the object of interest
  • Nonobjects similar in appearance to the object of interest

The system toolbox provides an app to select and assign regions of interest (ROI) and label training images.

Training image labeler app to select regions of interest (ROIs) in positive training images
Training image labeler app to select regions of interest (ROIs) in positive training images.

The system toolbox provides functions to train a Viola-Jones object detector to locate any object of interest. An app to train a detector is available on File Exchange.

Process of training a cascade object detector.
Process of training a cascade object detector.
Next: Object Tracking and Motion Estimation

Try Computer Vision System Toolbox

Get trial software

Computer Vision Made Easy

View webinar