Recognition, Object Detection, and Semantic Segmentation
Computer Vision Toolbox™ supports several approaches for image classification, object detection, semantic segmentation, instance 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
- Object Detection
Perform classification, object detection, transfer learning using convolutional neural networks (CNNs, or ConvNets), create customized detectors
- Semantic Segmentation
Semantic image segmentation
- Instance Segmentation
Perform instance segmentation using pretrained deep learning networks and train networks using transfer learning on custom data
- Image Category Classification
Create vision transformer or bag of visual words image classifier
- Automated Visual Inspection
Automate quality control tasks using anomaly detection and localization methods
- Text Detection and Recognition
Detect and recognize text using image feature detection and description, deep learning, and OCR
- Keypoint Detection
Detect keypoints in objects using convolutional neural networks (CNNs)
- Video Classification
Perform video classification and activity recognition using deep learning
Featured Examples
Multiclass Object Detection Using YOLO v2 Deep Learning
Train a YOLO v2 multiclass object detector and evaluate object detector performance across selected classes and overlap thresholds.
Semantic Segmentation Using Deep Learning
Segment an image using a semantic segmentation network.
Perform Instance Segmentation Using Mask R-CNN
Segment individual instances of people and cars using a multiclass mask region-based convolutional neural network (R-CNN).
Perform 6-DoF Pose Estimation for Bin Picking Using Deep Learning
Perform six degrees-of-freedom (6-DoF) pose estimation by estimating the 3-D position and orientation of machine parts in a bin using RGB-D images and a deep learning network.
Activity Recognition from Video and Optical Flow Data Using Deep Learning
Train an inflated-3D (I3D) two-stream convolutional neural network for activity recognition using RGB and optical flow data from videos.
Automatically Detect and Recognize Text Using Pretrained CRAFT Network and OCR
Perform text recognition by using a deep learning based text detector and OCR.
Train Vision Transformer Network for Image Classification
Fine-tune a pretrained vision transformer (ViT) neural network to perform classification on a new collection of images.
Detect Small Objects Using Tiled Training of YOLOX Network
Detect small objects in full-resolution images using tiled training of a you only look once version X (YOLOX) deep learning network.
