帮助中心帮助中心

本页翻译不是最新的。点击此处可查看最新英文版本。

图像处理

利用图像处理应用扩展深度学习工作流

通过将 Deep Learning Toolbox™ 与 Image Processing Toolbox™ 结合使用，将深度学习应用于图像处理应用。

函数

`augmentedImageDatastore`	变换批量以增强图像数据
`randomPatchExtractionDatastore`	Datastore for extracting random 2-D or 3-D random patches from images or pixel label images
`blockedImageDatastore`	Datastore for use with blocks from `blockedImage` objects (自 R2021a 起)

主题

Preprocess Data for Domain-Specific Deep Learning Applications
Perform deterministic or randomized data processing for domains such as image processing, object detection, semantic segmentation, signal and audio processing, and text analytics.
Augment Images for Deep Learning Workflows
This example shows how you can perform common kinds of randomized image augmentation such as geometric transformations, cropping, and adding noise.
预处理图像以进行深度学习
了解如何调整图像大小以进行训练、预测和分类，以及如何使用数据增强、变换和专用数据存储对图像进行预处理。
Preprocess Volumes for Deep Learning
Read and preprocess volumetric image and label data for 3-D deep learning.
Preprocess Multiresolution Images for Training Classification Network (Image Processing Toolbox)
This example shows how to prepare datastores that read and preprocess multiresolution whole slide images (WSIs) that might not fit in memory.
Get Started with GANs for Image-to-Image Translation (Image Processing Toolbox)
Transfer styles and characteristics from one set of images to the scene content of other images by using generative adversarial networks (GANs).

精选示例

使用深度学习增加图像分辨率

使用深度学习增加图像分辨率

此示例说明如何使用超深超分辨率 (VDSR) 神经网络从低分辨率图像创建高分辨率图像。

打开实时脚本

使用深度学习进行图像处理算子逼近

使用深度学习进行图像处理算子逼近

此示例说明如何使用多尺度上下文聚合网络 (CAN) 逼近图像滤波运算。

打开实时脚本

Develop Camera Processing Pipeline Using Deep Learning

Develop Camera Processing Pipeline Using Deep Learning

Convert RAW camera data to an aesthetically pleasing color image using a U-Net.

打开实时脚本

Brighten Extremely Dark Images Using Deep Learning

Brighten Extremely Dark Images Using Deep Learning

Recover brightened RGB images from RAW camera data collected in extreme low-light conditions using a U-Net.

打开实时脚本

Unsupervised Day-to-Dusk Image Translation Using UNIT

Unsupervised Day-to-Dusk Image Translation Using UNIT

Translate images between daytime and dusk lighting conditions using an unsupervised image-to-image translation network (UNIT).

打开实时脚本

Quantify Image Quality Using Neural Image Assessment

Quantify Image Quality Using Neural Image Assessment

Analyze the aesthetic quality of images using a Neural Image Assessment (NIMA) convolutional neural network (CNN).

打开实时脚本

Classify Tumors in Multiresolution Blocked Images

Classify Tumors in Multiresolution Blocked Images

Classify multiresolution whole slide images (WSIs) that might not fit in memory using an Inception-v3 deep neural network.

打开实时脚本

使用深度学习对多光谱图像进行语义分割

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。

打开实时脚本

使用深度学习进行 JPEG 图像去块

使用深度学习进行 JPEG 图像去块

此示例说明如何使用去噪卷积神经网络 (DnCNN) 来减少图像中的 JPEG 压缩伪影。

打开实时脚本

使用预训练的神经网络去除彩色图像中的噪声

使用预训练的神经网络去除彩色图像中的噪声

此示例说明如何使用去噪卷积神经网络从 RGB 图像中去除高斯噪声。

打开实时脚本

使用深度学习的神经样式迁移

使用深度学习的神经样式迁移

此示例说明如何使用预训练的 VGG-19 网络将一个图像的样式外观应用于另一个图像的场景内容。

打开实时脚本

Train Fast Style Transfer Network

Train Fast Style Transfer Network

Train a network to transfer the style of an image to a second image. It is based on the architecture defined in [1].

打开实时脚本

Ship Detection from Sentinel-1 C Band SAR Data Using YOLOX Object Detection

Ship Detection from Sentinel-1 C Band SAR Data Using YOLOX Object Detection

Detect ships from Sentinel-1 C Band SAR Data using YOLOX object detection.

打开实时脚本