图像检索之IF-IDF,RootSift,VLAD

void compute_idf(const vector<<vector<int>> &bow,vector<float> &idf){

    int img_count = bow.size();
    int clu_count = bow[0].size();

    idf = vector<float>(clu_count,1.0);

    for(int i = 0; i < img_count; i ++){
        for(int j = 0; j < clu_count; j ++){
            if(bow[i][j] != 0) idf[j] ++;
        }
    }

    for(int i = 0; i < idf.size(); i ++){
        idf[i] = log(img_count / idf[i]);
    }
}

void compute_tf(const vector<int> &bow,vector<float> &tf){

    tf = vector<float>(bow.size(),0);

    int sum = 0; // All words in the image
    for(int i = 0; i < bow.size(); i ++){
        sum += bow[i];
    }

    for(int i = 0; i < bow.size(); i ++){
        tf[i] = (float)bow[i] / sum; 
    }
}

# import the necessary packages
import numpy as np
import cv2

class RootSIFT:
    def __init__(self):
        # initialize the SIFT feature extractor
        self.extractor = cv2.DescriptorExtractor_create("SIFT")

    def compute(self, image, kps, eps=1e-7):
        # compute SIFT descriptors
        (kps, descs) = self.extractor.compute(image, kps)

        # if there are no keypoints or descriptors, return an empty tuple
        if len(kps) == 0:
            return ([], None)

        # apply the Hellinger kernel by first L1-normalizing and taking the
        # square-root
        descs /= (descs.sum(axis=1, keepdims=True) + eps)
        descs = np.sqrt(descs)
        #descs /= (np.linalg.norm(descs, axis=1, ord=2) + eps)

        # return a tuple of the keypoints and descriptors
        return (kps, descs)

for(int i = 0; i < siftFeature.rows; i ++){
        // Conver to float type
        Mat f;
        siftFeature.row(i).convertTo(f,CV_32FC1);

        normalize(f,f,1,0,NORM_L1); // l1 normalize
        sqrt(f,f); // sqrt-root  root-sift
        rootSiftFeature.push_back(f);
    }

void Vocabulary::transform_vlad(const cv::Mat &f,cv::Mat &vlad)
{
    // Find the nearest center
    Ptr<FlannBasedMatcher> matcher = FlannBasedMatcher::create();
    vector<DMatch> matches;
    matcher->match(f,m_voc,matches);


    // Compute vlad
    Mat responseHist(m_voc.rows,f.cols,CV_32FC1,Scalar::all(0));
    for( size_t i = 0; i < matches.size(); i++ ){
        auto queryIdx = matches[i].queryIdx;
        int trainIdx = matches[i].trainIdx; // cluster index
        Mat residual;
        subtract(f.row(queryIdx),m_voc.row(trainIdx),residual,noArray());
        add(responseHist.row(trainIdx),residual,responseHist.row(trainIdx),noArray(),responseHist.type());
    }

    // l2-norm
    auto l2 = norm(responseHist,NORM_L2);
    responseHist /= l2;
    //normalize(responseHist,responseHist,1,0,NORM_L2);

    //Mat vec(1,m_voc.rows * f.cols,CV_32FC1,Scalar::all(0));
    vlad = responseHist.reshape(0,1); // Reshape the matrix to 1 x (k*d) vector
}