【问题标题】：How to add HOG features into matrix (matlab)如何将 HOG 特征添加到矩阵中（matlab）
【发布时间】：2015-05-20 15:01:25
【问题描述】：

提取图像文件夹的 HOG 特征后，我想将所有这些结果添加到一个矩阵中。我怎么能做到这一点？这是我在 matlab 中的代码：

training_female = 'E:\Training Set\Female Images';

% read all images with specified extention, its jpg in our case
filenames = dir(fullfile(training_female, '*.jpg'));

% count total number of photos present in that folder
total_images = numel(filenames);

for n = 1:total_images

% Specify images names with full path and extension    
full_name= fullfile(training_female, filenames(n).name);

% Read images
training_images = imread(full_name);
[featureVector, hogVisualization] = extractHOGFeatures(training_images);
figure (n)

    % Show all images
    imshow(training_images); hold on;                  
    plot(hogVisualization);
end

【问题讨论】：

您尝试将其加载到矩阵中但不起作用的代码在哪里？
我刚刚准备了上面的代码，它读取并提取了一组图像的 Hog 特征。我需要帮助来创建矩阵并在其中添加 HoG 功能。
我认为这个页面可以帮助你：geocities.ws/talh_davidc

标签： matlab image-processing matrix computer-vision matlab-cvst

【解决方案1】：

通过查看documentation，调用extractHOGFeatures 计算给定输入图像的1 x N 向量。因为计算它的输出大小可能有点麻烦，这还取决于您为 HOG 检测器设置的参数，最好先创建一个空矩阵并在每次迭代时动态连接特征。通常，如果您想在迭代的基础上填充元素，您会预先分配一个矩阵以提高性能。不这样做会使性能略有下降，但考虑到您的情况，它是最适应的。您可能想要调整 HOG 参数，如果我们以动态方式进行调整，则无需确定矩阵的总大小应该是多少。

所以做这样的事情。我已将 %//New 标签放在我修改过您的代码的位置：

training_female = 'E:\Training Set\Female Images';

% read all images with specified extention, its jpg in our case
filenames = dir(fullfile(training_female, '*.jpg'));

% count total number of photos present in that folder
total_images = numel(filenames);

featureMatrix = []; %// New - Declare feature matrix

for n = 1:total_images

    % Specify images names with full path and extension    
    full_name= fullfile(training_female, filenames(n).name);

    % Read images
    training_images = imread(full_name);
    [featureVector, hogVisualization] = extractHOGFeatures(training_images);

    %// New - Add feature vector to matrix
    featureMatrix = [featureMatrix; featureVector];
    figure(n);

    % Show all images
    imshow(training_images); hold on;                  
    plot(hogVisualization);
end

featureMatrix 将包含您的 HOG 特征，其中每一行代表每个图像。因此，对于特定图像i，您可以通过以下方式确定 HOG 特征：

feature = featureMatrix(i,:);

警告

我需要提一下，上面的代码假定您目录中的所有图像大小相同。如果不是，那么每个 HOG 调用的输出向量大小将会不同。如果是这种情况，您将需要一个元胞数组来适应不同的大小。

因此，请执行以下操作：

training_female = 'E:\Training Set\Female Images';

% read all images with specified extention, its jpg in our case
filenames = dir(fullfile(training_female, '*.jpg'));

% count total number of photos present in that folder
total_images = numel(filenames);

featureMatrix = cell(1,total_images); %// New - Declare feature matrix

for n = 1:total_images

    % Specify images names with full path and extension    
    full_name= fullfile(training_female, filenames(n).name);

    % Read images
    training_images = imread(full_name);
    [featureVector, hogVisualization] = extractHOGFeatures(training_images);

    %// New - Add feature vector to matrix
    featureMatrix{n} = featureVector;
    figure(n);

    % Show all images
    imshow(training_images); hold on;                  
    plot(hogVisualization);
end

要访问特定图像的功能或图像i，请执行以下操作：

feature = featureMatrix{i};

【讨论】：

我接受了。真的再次感谢rayryeng先生。