计算机视觉

利用计算机视觉应用扩展深度学习工作流

通过将 Computer Vision Toolbox™ 与 Deep Learning Toolbox™ 结合使用，将深度学习应用于计算机视觉应用。

App

图像标注器	Label images for computer vision applications
视频标注器	Label video for computer vision applications

函数

全部展开

训练数据的数据存储

`boxLabelDatastore`	Datastore for bounding box label data (自 R2019b 起)
`pixelLabelDatastore`	Datastore for pixel label data

ViT（视觉变换器）

`visionTransformer`	Pretrained vision transformer (ViT) neural network (自 R2023b 起)
`patchEmbeddingLayer`	Patch embedding layer (自 R2023b 起)

语义分割

`deeplabv3plusLayers`	(To be removed) Create DeepLab v3+ convolutional neural network for semantic image segmentation (自 R2019b 起)
`segnetLayers`	(To be removed) Create SegNet layer graph for semantic segmentation
`unetLayers`	(To be removed) Create U-Net layers for semantic segmentation
`unet3dLayers`	(To be removed) Create 3-D U-Net layers for semantic segmentation of volumetric images (自 R2019b 起)

目标检测和实例分割

`rcnnObjectDetector`	Detect objects using R-CNN deep learning detector
`fastRCNNObjectDetector`	Detect objects using Fast R-CNN deep learning detector
`fasterRCNNObjectDetector`	Detect objects using Faster R-CNN deep learning detector
`ssdObjectDetector`	Detect objects using SSD deep learning detector (自 R2020a 起)
`yolov2ObjectDetector`	Detect objects using YOLO v2 object detector
`yolov3ObjectDetector`	Detect objects using YOLO v3 object detector (自 R2021a 起)
`yolov4ObjectDetector`	Detect objects using YOLO v4 object detector (自 R2022a 起)
`solov2`	Segment objects using SOLOv2 instance segmentation network (自 R2023b 起)
`maskrcnn`	Detect objects using Mask R-CNN instance segmentation (自 R2021b 起)

自动化视觉检查

`fcddAnomalyDetector`	Detect anomalies using fully convolutional data description (FCDD) network for anomaly detection (自 R2022b 起)
`fastFlowAnomalyDetector`	Detect anomalies using FastFlow network (自 R2023a 起)
`patchCoreAnomalyDetector`	Detect anomalies using PatchCore network (自 R2023a 起)
`yoloxObjectDetector`	Detect objects using YOLOX object detector (自 R2023b 起)

文本检测和识别

detectTextCRAFT Detect texts in images by using CRAFT deep learning model (自 R2022a 起)

主题

图像分类

Train Vision Transformer Network for Image Classification
This example shows how to fine-tune a pretrained vision transformer (ViT) neural network neural network to perform classification on a new collection of images.

目标检测和实例分割

Getting Started with Object Detection Using Deep Learning (Computer Vision Toolbox)
Perform object detection using deep learning neural networks.
Augment Bounding Boxes for Object Detection
This example shows how to perform common kinds of image and bounding box augmentation as part of object detection workflows.
Get Started with SOLOv2 for Instance Segmentation (Computer Vision Toolbox)
Perform multiclass instance segmentation using SOLOv2 and deep learning.
使用 R-CNN 深度学习训练目标检测器
此示例说明如何使用深度学习和 R-CNN（区域卷积神经网络）训练目标检测器。
Import Pretrained ONNX YOLO v2 Object Detector
This example shows how to import a pretrained ONNX™ (Open Neural Network Exchange) you only look once (YOLO) v2 [1] object detection network and use it to detect objects.
Export YOLO v2 Object Detector to ONNX
This example shows how to export a YOLO v2 object detection network to ONNX™ (Open Neural Network Exchange) model format.
Deploy Object Detection Model as Microservice (MATLAB Compiler SDK)
Use a microservice to detect objects in images.

自动化视觉检查

Getting Started with Anomaly Detection Using Deep Learning (Computer Vision Toolbox)
Anomaly detection using deep learning is an increasingly popular approach to automating visual inspection tasks.
Detect Image Anomalies Using Explainable FCDD Network
Use an anomaly detector to distinguish between normal pills and pills with anomalous chips or contamination.
Classify Defects on Wafer Maps Using Deep Learning
This example shows how to classify eight types of manufacturing defects on wafer maps using a simple convolutional neural network (CNN).
Detect Image Anomalies Using Pretrained ResNet-18 Feature Embeddings
Train a similarity-based anomaly detector using one-class learning of feature embeddings extracted from a pretrained ResNet-18 convolutional neural network.
Localize Industrial Defects Using PatchCore Anomaly Detector
Perform localization of anomalous defects in printed circuit boards (PCBs) using anomaly heat maps generated with the PatchCore anomaly detector.

语义分割

Getting Started with Semantic Segmentation Using Deep Learning (Computer Vision Toolbox)
Segment objects by class using deep learning.
Augment Pixel Labels for Semantic Segmentation
This example shows how to perform common kinds of image and pixel label augmentation as part of semantic segmentation workflows.
使用扩张卷积进行语义分割
使用扩张卷积训练语义分割网络。
使用深度学习对多光谱图像进行语义分割
此示例说明如何使用 U-Net 对包含七个通道的多光谱图像执行语义分割。
使用深度学习进行三维脑肿瘤分割
此示例说明如何基于三维医学图像执行脑肿瘤的语义分割。
定义使用 Tversky 损失的自定义像素分类层
此示例说明如何定义和创建使用 Tversky 损失的自定义像素分类层。
Explore Semantic Segmentation Network Using Grad-CAM
This example shows how to explore the predictions of a pretrained semantic segmentation network using Grad-CAM.
Generate Adversarial Examples for Semantic Segmentation (Computer Vision Toolbox)
Generate adversarial examples for a semantic segmentation network using the basic iterative method (BIM).
Prune and Quantize Semantic Segmentation Network
Reduce the memory footprint of a semantic segmentation network and speed-up inference by compressing the network using pruning and quantization.

视频分类

Activity Recognition from Video and Optical Flow Data Using Deep Learning
This example first shows how to perform activity recognition using a pretrained Inflated 3-D (I3D) two-stream convolutional neural network based video classifier and then shows how to use transfer learning to train such a video classifier using RGB and optical flow data from videos [1].
Gesture Recognition using Videos and Deep Learning
Perform gesture recognition using a pretrained SlowFast video classifier.

精选示例

Detect Defects on Printed Circuit Boards Using YOLOX Network

Detect, localize, and classify defects in printed circuit boards (PCBs) using a you only look once version X (YOLOX) deep learning network.

打开实时脚本

使用 YOLO v2 深度学习进行目标检测

此示例说明如何训练 you only look once (YOLO) v2 目标检测器。

打开实时脚本

Perform Instance Segmentation Using SOLOv2

Segment object instances of randomly rotated machine parts in a bin using a deep learning SOLOv2 network.

Point Cloud Classification Using PointNet Deep Learning

Train a PointNet network for point cloud classification.

打开实时脚本

Object Detection Using SSD Deep Learning

Train a Single Shot Detector (SSD).

打开实时脚本

Object Detection Using YOLO v3 Deep Learning

Train a YOLO v3 object detector using custom training loop.

打开实时脚本

Object Detection Using YOLO v4 Deep Learning

Detect objects in images using you only look once version 4 (YOLO v4) deep learning network. In this example, you will

打开实时脚本

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).

打开实时脚本

使用深度学习进行语义分割

此示例说明如何使用语义分割网络来分割图像。

打开实时脚本

Generate Image from Segmentation Map Using Deep Learning

Generate a synthetic image of a scene from a semantic segmentation map.

打开实时脚本

Estimate Body Pose Using Deep Learning

Estimate the body pose of one or more people using the OpenPose algorithm.

打开实时脚本

Activity Recognition from Video and Optical Flow Data Using Deep Learning

First shows how to perform activity recognition using a pretrained Inflated 3-D (I3D) two-stream convolutional neural network based video classifier and then shows how to use transfer learning to train such a video classifier using RGB and optical flow data from videos [1].

打开实时脚本