Resize Image and Pixel Labels

您可以使用imresize函数。Resize the image and the pixel label image to the same size, and display the labels over the image.

targetsize = [300 300];resizedI = imresize(I,targetSize); resizedC = imresize(C,targetSize);

Display the resized labels over the resized image.

B = labeloverlay(resizedI,resizedC); imshow(B) title(“调整图像和像素标签”）

作物图像和像素标签

裁剪是使数据与网络的输入大小相匹配的常见预处理步骤。要创建所需尺寸的输出图像，请首先使用RandomWindow2D(Image Processing Toolbox)和Centercropwindow2d(Image Processing Toolbox)功能。确保选择一个裁剪窗口，其中包含图像中所需的内容。然后，通过使用图像和像素标签图像将图像裁剪到同一窗口imcrop。

Specify the desired size of the cropped region as a two-element vector of the form [高度，，，，width].

targetsize = [300 300];

将图像从图像中心裁剪到目标大小。

win = centerCropWindow2d（尺寸（i），targetsize）;croppedi = imcrop（i，win）;croppedc = imcrop（c，win）;

在裁剪图像上显示裁剪标签。

b = labeloverlay（croppedi，croppedc）;imshow（b）标题（“中心裁剪图像和像素标签”）

Crop the image to the target size from a random position in the image.

win = RandomWindow2d（size（i），targetsize）;croppedi = imcrop（i，win）;croppedc = imcrop（c，win）;

在裁剪图像上显示裁剪标签。

b = labeloverlay（croppedi，croppedc）;imshow（b）标题（'Random Cropped Image and Pixel Labels'）

经线图像和像素标签

这randomAffine2d(Image Processing Toolbox)function creates a randomized 2-D affine transformation from a combination of rotation, translation, scaling (resizing), reflection, and shearing. Apply the transformation to images and pixel label images by usingIMWARP(Image Processing Toolbox)。控制扭曲输出的空间界限和分辨率affineOutputView(Image Processing Toolbox)函数。

通过从[-50,50]度范围内随机选择的角度旋转输入图像和像素标签图像。

tform = RandomAffine2d（“回转”，[-50 50]）;

为扭曲的图像和像素标签图像创建输出视图。

dout = affineOutputView（size（i），tform）;

UseIMWARP旋转图像和像素标签图像。

rotatedI = imwarp(I,tform,'OutputView'，Rout）;rotatedc = imwarp（c，tform，'OutputView'，Rout）;

Display the rotated labels over the rotated image.

B = labeloverlay(rotatedI,rotatedC); imshow(B) title(“旋转图像和像素标签”）

Apply Augmentation to Semantic Segmentation Training Data in Datastores

Datastores are a convenient way to read and augment collections of images. Create a datastore that stores image and pixel label image data, and augment the data with a series of multiple operations.

创建包含图像和像素标签图像数据的数据存储

要增加样品数据存储的大小，请复制图像和像素标签图像的文件名。

numObservations = 4;trainimages = repelem（{filenameimage}，numobservations，1）;trainlabels = repelem（{filenamelabels}，numobservations，1）;

创建一个imageDatastorefrom the training image files. Create aPixellabeldatastore从培训像素标签文件中。数据存储包含多个相同数据的副本。

imds = imageDatastore(trainImages); pxds = pixelLabelDatastore(trainLabels,classes,ids);

通过组合图像数据存储和像素标签数据存储，将图像和像素标签对关联。

triendingdata = combine（imds，pxds）;

从组合数据存储中读取第一个图像及其关联的像素标签图像。

data = read（triendingdata）;i = data {1};C =数据{2};

显示图像和像素标签数据。

b = labeloverlay（i，c）;imshow（b）

应用数据增强

将数据扩展应用于培训数据转换函数。本例中执行两种布局方式te augmentations to the training data.

这first augmentation jitters the color of the image and then performs identical random scaling, horizontal reflection, and rotation on the image and pixel label image pairs. These operations are defined in thejitterImageColorAndWarp在此示例末尾的辅助功能。

augmentedTrainingData = transform（triendingdata，@jitterimagecolorandwarp）;

阅读所有增强数据。

data = readall（augmentedTrainingData）;

Display the augmented image and pixel label data.

RGB =单元格（NumObservations，1）;为了k = 1：numObservations i = data {k，1};c = data {k，2};rgb {k} = labeloverlay（i，c）;结尾蒙太奇（RGB）

这second augmentation center crops the image and pixel label image to a target size. These operations are defined in thecenterCropImageAndLabel在此示例末尾的辅助功能。

targetsize = [800 800];preprocessedTrainingData =变换（增强培养Data，...@(data)centerCropImageAndLabel(data,targetSize));

阅读所有预处理数据。

data = readall（预处理trainingdata）;

显示预处理图像和像素标签数据。

RGB =单元格（NumObservations，1）;为了k = 1：numObservations i = data {k，1};c = data {k，2};rgb {k} = labeloverlay（i，c）;结尾蒙太奇（RGB）

助手功能增强功能

这jitterImageColorAndWarphelper function applies random color jitter to the image data, then applies an identical affine transformation to the image and pixel label image data. The transformation consists of a random combination of scaling by a scale factor in the range [0.8 1.5], horizontal reflection, and rotation in the range [-30, 30] degrees. The inputdata和outputoutare two-element cell arrays, where the first element is the image data and the second element is the pixel label image data.

functionout = jitterImageColorAndWarp(data)% Unpack original data.i = data {1};C =数据{2};% Apply random color jitter.I = jitterColorHSV(I,“亮度”，，，，0.3,"Contrast"，，，，0.4,“饱和”，0.2）;％定义随机仿射变换。tform = RandomAffine2d（"Scale"，[0.8 1.5]，，“ X反射”，真的，'回转'，[-30 30]）;dout = affineOutputView（size（i），tform）;％变换图像和边界框标签。augmentedImage = imwarp（i，tform，"OutputView"，Rout）;augmentedlabel = imwarp（c，tform，"OutputView"，Rout）;％返回增强数据。out = {augmentedImage，augmentedlabel};结尾

这centerCropImageAndLabelhelper function creates a crop window centered on the image, then crops both the image and the pixel label image using the crop window. The inputdata和outputoutare two-element cell arrays, where the first element is the image data and the second element is the pixel label image data.

functionout = centerCropImageAndLabel(data,targetSize) win = centerCropWindow2d(size(data{1}),targetSize); out{1} = imcrop(data{1},win); out{2} = imcrop(data{2},win);结尾