opencv2笔记06-主成分分析（PCA）

最新推荐文章于 2022-07-22 08:00:00 发布

k_shmily

最新推荐文章于 2022-07-22 08:00:00 发布

阅读量678

点赞数

分类专栏： CV

本文链接：https://blog.csdn.net/k_shmily/article/details/52918253

版权

CV 专栏收录该内容

6 篇文章 0 订阅

订阅专栏

简介

PCA（Principal Components Analysis）即主成分分析，是图像处理中经常用到的降维方法，大家知道，我们在处理有关数字图像处理方面的问题时，比如经常用的图像的查询问题，在一个几万或者几百万甚至更大的数据库中查询一幅相近的图像。这时，我们通常的方法是对图像库中的图片提取响应的特征，如颜色，纹理，sift，surf，vlad等等特征，然后将其保存，建立响应的数据索引，然后对要查询的图像提取相应的特征，与数据库中的图像特征对比，找出与之最近的图片。

原理

假定有 m 个样本，每个样本有 n 个特征
\( x = [x^{(1)}, x^{(2)}, ... ,x^{(m)}]^T \), 其中每个样本为n维\( x^{(1)} = [x_1^{(1)}, x_2^{(1)},...,x_n^{(1)}] \)
1.计算特性的均值\( \mu_i \)(协方差矩阵是计算不同维度间的协方差，要时刻牢记这一点。样本矩阵的每行是一个样本，每列为一个维度，所以我们要按列计算均值。)
\( \mu_i = \frac{1}{m} \sum_{j=1}^{m} x_i^{(j)} \)
2.计算协方差矩阵\( S \)
\( S = \frac{1}{m-1} (x-\mu)^T (x-\mu) \) 得到nxn的协方差矩阵
3.计算矩阵\( S \)的特征值\( \lambda_i \)和特征向量\( v_i \)
\( S v_i = \lambda_i v_i, i =1,2,...,n\)
4.根据特征值的大小对特征向量进行排序，主成分就是最大的特征值对应的特征向量
然后评估向量的主成分就是：
\(y = W^Tx \)其中\(W =(v_1, v_2,...,v_k) \)

Eigenfaces方法进行人脸识别的主要步骤为：

1.将训练样本映射到PCA子空间
2.将测试样本映射到PCA空间
3.找到训练样本和测试样本间的最邻近值

static Mat norm_0_255(InputArray _src) {
    Mat src = _src.getMat();
    // Create and return normalized image:
    Mat dst;
    switch(src.channels()) {
    case 1:
        cv::normalize(_src, dst, 0, 255, NORM_MINMAX, CV_8UC1);
        break;
    case 3:
        cv::normalize(_src, dst, 0, 255, NORM_MINMAX, CV_8UC3);
        break;
    default:
        src.copyTo(dst);
        break;
    }
    return dst;
}

static void read_csv(const string& filename, vector<Mat>& images, vector<int>& labels, char separator = ';') {
    std::ifstream file(filename.c_str(), ifstream::in);
    if (!file) {
        string error_message = "No valid input file was given, please check the given filename.";
        CV_Error(CV_StsBadArg, error_message);
    }
    string line, path, classlabel;
    while (getline(file, line)) {
        stringstream liness(line);
        getline(liness, path, separator);
        getline(liness, classlabel);
        if(!path.empty() && !classlabel.empty()) {
            images.push_back(imread(path, 0));
            labels.push_back(atoi(classlabel.c_str()));
        }
    }
}

int eigenfaces(const char *argv1, const char *argv2) {
    // Check for valid command line arguments, print usage
    // if no arguments were given.
	int argc = 3;
/*
    if (argc < 2) {
        cout << "usage: " << argv[0] << " <csv.ext> <output_folder> " << endl;
        exit(1);
    }
*/
    string output_folder = ".";
    if (argc == 3) {
        output_folder = string(argv2);
    }
    // Get the path to your CSV.
    string fn_csv = string(argv1);
    // These vectors hold the images and corresponding labels.
    vector<Mat> images;
    vector<int> labels;
    // Read in the data. This can fail if no valid
    // input filename is given.
    try {
        read_csv(fn_csv, images, labels);
    } catch (cv::Exception& e) {
        cerr << "Error opening file \"" << fn_csv << "\". Reason: " << e.msg << endl;
        // nothing more we can do
        exit(1);
    }
    // Quit if there are not enough images for this demo.
    if(images.size() <= 1) {
        string error_message = "This demo needs at least 2 images to work. Please add more images to your data set!";
        CV_Error(CV_StsError, error_message);
    }
    // Get the height from the first image. We'll need this
    // later in code to reshape the images to their original
    // size:
    int height = images[0].rows;
    // The following lines simply get the last images from
    // your dataset and remove it from the vector. This is
    // done, so that the training data (which we learn the
    // cv::FaceRecognizer on) and the test data we test
    // the model with, do not overlap.
    Mat testSample = images[images.size() - 1];
    int testLabel = labels[labels.size() - 1];
    images.pop_back();
    labels.pop_back();
    // The following lines create an Eigenfaces model for
    // face recognition and train it with the images and
    // labels read from the given CSV file.
    // This here is a full PCA, if you just want to keep
    // 10 principal components (read Eigenfaces), then call
    // the factory method like this:
    //
    //      cv::createEigenFaceRecognizer(10);
    //
    // If you want to create a FaceRecognizer with a
    // confidence threshold (e.g. 123.0), call it with:
    //
    //      cv::createEigenFaceRecognizer(10, 123.0);
    //
    // If you want to use _all_ Eigenfaces and have a threshold,
    // then call the method like this:
    //
    //      cv::createEigenFaceRecognizer(0, 123.0);
    //
    Ptr<FaceRecognizer> model = createEigenFaceRecognizer();
    model->train(images, labels);
    // The following line predicts the label of a given
    // test image:
    int predictedLabel = model->predict(testSample);
    //
    // To get the confidence of a prediction call the model with:
    //
    //      int predictedLabel = -1;
    //      double confidence = 0.0;
    //      model->predict(testSample, predictedLabel, confidence);
    //
    string result_message = format("Predicted class = %d / Actual class = %d.", predictedLabel, testLabel);
    cout << result_message << endl;
    // Here is how to get the eigenvalues of this Eigenfaces model:
    Mat eigenvalues = model->getMat("eigenvalues");
    // And we can do the same to display the Eigenvectors (read Eigenfaces):
    Mat W = model->getMat("eigenvectors");
    // Get the sample mean from the training data
    Mat mean = model->getMat("mean");
    // Display or save:
    if(argc == 2) {
        imshow("mean", norm_0_255(mean.reshape(1, images[0].rows)));
    } else {
        imwrite(format("%s/mean.png", output_folder.c_str()), norm_0_255(mean.reshape(1, images[0].rows)));
    }
    // Display or save the Eigenfaces:
    for (int i = 0; i < min(10, W.cols); i++) {
        string msg = format("Eigenvalue #%d = %.5f", i, eigenvalues.at<double>(i));
        cout << msg << endl;
        // get eigenvector #i
        Mat ev = W.col(i).clone();
        // Reshape to original size & normalize to [0...255] for imshow.
        Mat grayscale = norm_0_255(ev.reshape(1, height));
        // Show the image & apply a Jet colormap for better sensing.
        Mat cgrayscale;
        applyColorMap(grayscale, cgrayscale, COLORMAP_JET);
        // Display or save:
        if(argc == 2) {
            imshow(format("eigenface_%d", i), cgrayscale);
        } else {
            imwrite(format("%s/eigenface_%d.png", output_folder.c_str(), i), norm_0_255(cgrayscale));
        }
    }

    // Display or save the image reconstruction at some predefined steps:
    for(int num_components = min(W.cols, 10); num_components < min(W.cols, 300); num_components+=15) {
        // slice the eigenvectors from the model
        Mat evs = Mat(W, Range::all(), Range(0, num_components));
        Mat projection = subspaceProject(evs, mean, images[0].reshape(1,1));
        Mat reconstruction = subspaceReconstruct(evs, mean, projection);
        // Normalize the result:
        reconstruction = norm_0_255(reconstruction.reshape(1, images[0].rows));
        // Display or save:
        if(argc == 2) {
            imshow(format("eigenface_reconstruction_%d", num_components), reconstruction);
        } else {
            imwrite(format("%s/eigenface_reconstruction_%d.png", output_folder.c_str(), num_components), reconstruction);
        }
    }
    // Display if we are not writing to an output folder:
    if(argc == 2) {
        waitKey(0);
    }
    return 0;
}

Reference:
[1] http://docs.opencv.org/2.4/modules/contrib/doc/facerec/facerec_tutorial.html
[2] http://blog.csdn.net/watkinsong/article/details/38536463
[3] http://blog.csdn.net/celerychen2009/article/details/9048033
[4] http://www.cnblogs.com/tornadomeet/archive/2012/09/06/2673104.html