Main Content

Computer Vision

Extend deep learning workflows with computer vision applications

Apply deep learning to computer vision applications by using Deep Learning Toolbox™ together with the Computer Vision Toolbox™.


Image LabelerLabel images for computer vision applications
Video LabelerLabel video for computer vision applications


expand all

boxLabelDatastoreDatastore for bounding box label data (Since R2019b)
pixelLabelDatastoreDatastore for pixel label data
visionTransformerPretrained vision transformer (ViT) neural network (Since R2023b)
patchEmbeddingLayerPatch embedding layer (Since R2023b)
unetCreate U-Net convolutional neural network for semantic segmentation (Since R2024a)
unet3dCreate 3-D U-Net convolutional neural network for semantic segmentation of volumetric images (Since R2024a)
deeplabv3plusCreate DeepLab v3+ convolutional neural network for semantic image segmentation (Since R2024a)
rcnnObjectDetectorDetect objects using R-CNN deep learning detector
fastRCNNObjectDetectorDetect objects using Fast R-CNN deep learning detector
fasterRCNNObjectDetectorDetect objects using Faster R-CNN deep learning detector
ssdObjectDetectorDetect objects using SSD deep learning detector (Since R2020a)
yolov2ObjectDetectorDetect objects using YOLO v2 object detector
yolov3ObjectDetectorDetect objects using YOLO v3 object detector (Since R2021a)
yolov4ObjectDetectorDetect objects using YOLO v4 object detector (Since R2022a)
solov2Segment objects using SOLOv2 instance segmentation network (Since R2023b)
maskrcnnDetect objects using Mask R-CNN instance segmentation (Since R2021b)
posemaskrcnnPredict object pose using Pose Mask R-CNN pose estimation (Since R2024a)
reidentificationNetworkRe-identification deep learning network for re-identifying and tracking objects (Since R2024a)
fcddAnomalyDetectorDetect anomalies using fully convolutional data description (FCDD) network for anomaly detection (Since R2022b)
fastFlowAnomalyDetectorDetect anomalies using FastFlow network (Since R2023a)
patchCoreAnomalyDetectorDetect anomalies using PatchCore network (Since R2023a)
yoloxObjectDetectorDetect objects using YOLOX object detector (Since R2023b)
detectTextCRAFTDetect texts in images by using CRAFT deep learning model (Since R2022a)


Image Classification

Object Detection and Instance Segmentation

Automated Visual Inspection

Semantic Segmentation

Video Classification