Recognition, Object Detection, and Semantic Segmentation
Computer Vision Toolbox™ supports several approaches for image classification, object detection, semantic segmentation, and recognition, including:
Deep learning and convolutional neural networks (CNNs)
Bag of features
Template matching
Blob analysis
Viola-Jones algorithm
A CNN is a popular deep learning architecture that automatically learns useful feature representations directly from image data. Bag of features encodes image features into a compact representation suitable for image classification and image retrieval. Template matching uses a small image, or template, to find matching regions in a larger image. Blob analysis uses segmentation and blob properties to identify objects of interest. The Viola-Jones algorithm uses Haar-like features and a cascade of classifiers to identify objects, including faces, noses, and eyes. You can train this classifier to recognize other objects.
Categories
- Semantic Segmentation
Semantic image segmentation
- Object Detection
Perform classification, object detection, transfer learning using convolutional neural networks (CNNs, or ConvNets), create customized detectors
- Keypoint Detection
Detect keypoints in objects using convolutional neural networks (CNNs)
- Text Detection and Recognition
Detect and recognize text using image feature detection and description, deep learning, and OCR
- Image Category Classification
Create vision transformer or bag of visual words image classifier
- Video Classification
Perform video classification and activity recognition using deep learning
- Automated Visual Inspection
Automate quality control tasks using anomaly detection and localization methods