博客
关于我
5.11 用颜色和关键点对斑点进行分类
阅读量:700 次
发布时间:2019-03-21

本文共 4392 字,大约阅读时间需要 14 分钟。

斑点分类器是一个基于直方图和关键点的多分类器,该分类器能够根据输入图像中的斑点生成相应的分类结果。该分类器通过计算输入图像中的特征描述符,并与已知描述符进行比较,来确定图像所属的类别。

常量定义

#include "BlobClassifier.hpp"#include 
#include
#ifdef WITH_OPENCV_CONTRIB#include
#endifconst int HISTOGRAM_NUM_BINS_PER_CHANNEL = 32;const int HISTOGRAM_COMPARISON_METHOD = cv::HISTCMP_CHISQR_ALT;const float HISTOGRAM_DISTANCE_WEIGHT = 0.98f;const float KEYPOINT_MATCHING_DISTANCE_WEIGHT = 1.0f - HISTOGRAM_DISTANCE_WEIGHT;

构造函数

BlobClassifier::BlobClassifier() : clahe(cv::createCLAHE()) {    #ifdef WITH_OPENCV_CONTRIB        , featureDetectorAndDescriptorExtractor(cv::xfeatures2d::SURF::create())        , descriptorMatcher(cv::DescriptorMatcher::create("FlannBased"))    #else        , featureDetectorAndDescriptorExtractor(cv::ORB::create())        , descriptorMatcher(cv::DescriptorMatcher::create("BruteForce-HammingLUT"))    #endif}

更新方法

void BlobClassifier::update(const Blob &referenceBlob) {    referenceBlobDescriptors.push_back(createBlobDescriptor(referenceBlob));}

清空方法

void BlobClassifier::clear() {    referenceBlobDescriptors.clear();}

分类方法

void BlobClassifier::classify(Blob &detectedBlob) const {    BlobDescriptor detectedBlobDescriptor = createBlobDescriptor(detectedBlob);    float bestDistance = FLT_MAX;    uint32_t bestLabel = 0;    for (const BlobDescriptor &referenceBlobDescriptor : referenceBlobDescriptors) {        float distance = findDistance(detectedBlobDescriptor, referenceBlobDescriptor);        if (distance < bestDistance) {            bestDistance = distance;            bestLabel = referenceBlobDescriptor.getLabel();        }    }    detectedBlob.setLabel(bestLabel);}

创建描述符辅助方法

BlobDescriptor BlobClassifier::createBlobDescriptor(const Blob &blob) const {    const cv::Mat &mat = blob.getMat();    int numChannels = mat.channels();    // Calculate the histogram of the blob's image.    cv::Mat histogram;    int channels[] = {0, 1, 2};    int numBins[] = {HISTOGRAM_NUM_BINS_PER_CHANNEL, HISTOGRAM_NUM_BINS_PER_CHANNEL, HISTOGRAM_NUM_BINS_PER_CHANNEL};    float range[] = {0.0f, 256.0f};    const float *ranges[] = {range, range, range};    cv::calcHist(&mat, 1, channels, cv::Mat(), histogram, 3, numBins, ranges);    // Normalize the histogram.    histogram *= (1.0f / (mat.rows * mat.cols));    // Convert the blob's image to grayscale.    cv::Mat grayMat;    switch (numChannels) {        case 4:            cv::cvtColor(mat, grayMat, cv::COLOR_BGRA2GRAY);            break;        default:            cv::cvtColor(mat, grayMat, cv::COLOR_BGR2GRAY);            break;    }    // Detect features in the grayscale image.    std::vector
keypoints; featureDetectorAndDescriptorExtractor->detect(grayMat, keypoints); // Extract descriptors of the features. cv::Mat keypointDescriptors; featureDetectorAndDescriptorExtractor->compute(grayMat, keypoints, keypointDescriptors); return BlobDescriptor(histogram, keypointDescriptors, blob.getLabel());}

计算距离辅助方法

float BlobClassifier::findDistance(const BlobDescriptor &detectedBlobDescriptor, const BlobDescriptor &referenceBlobDescriptor) const {    float histogramDistance = (float)cv::compareHist(detectedBlobDescriptor.getNormalizedHistogram(), referenceBlobDescriptor.getNormalizedHistogram(), HISTOGRAM_COMPARISON_METHOD);    float keypointMatchingDistance = 0.0f;    std::vector
keypointMatches; descriptorMatcher->match(detectedBlobDescriptor.getKeypointDescriptors(), referenceBlobDescriptor.getKeypointDescriptors(), keypointMatches); for (const cv::dmatch &keypointMatch : keypointMatches) { keypointMatchingDistance += keypointMatch.distance; } return histogramDistance * HISTOGRAM_DISTANCE_WEIGHT + keypointMatchingDistance * KEYPOINT_MATCHING_DISTANCE_WEIGHT;}

BlobDescriptor类

#include "BlobDescriptor.hpp"BlobDescriptor::BlobDescriptor(const cv::Mat &normalizedHistogram, const cv::Mat &keypointDescriptors, uint32_t label) : normalizedHistogram(normalizedHistogram), keypointDescriptors(keypointDescriptors), label(label) {}const cv::Mat &BlobDescriptor::getNormalizedHistogram() const {    return normalizedHistogram;}const cv::Mat &BlobDescriptor::getKeypointDescriptors() const {    return keypointDescriptors;}uint32_t BlobDescriptor::getLabel() const {    return label;}

该分类器通过将图像转换为灰度并提取特征来进行分类。特征包括颜色直方图和关键点描述符。直方图和关键点的匹配距离结合计算,用于最终分类结果。代码采用了不同的特征检测算法(如SURF或ORB)以及相应的描述符匹配方法,以适应不同的性能需求。

转载地址:http://lqxez.baihongyu.com/

你可能感兴趣的文章
Mysql5.7深入学习 1.MySQL 5.7 中的新增功能
查看>>
Webpack 之 basic chunk graph
查看>>
Mysql5.7版本单机版my.cnf配置文件
查看>>
mysql5.7的安装和Navicat的安装
查看>>
mysql5.7示例数据库_Linux MySQL5.7多实例数据库配置
查看>>
Mysql8 数据库安装及主从配置 | Spring Cloud 2
查看>>
mysql8 配置文件配置group 问题 sql语句group不能使用报错解决 mysql8.X版本的my.cnf配置文件 my.cnf文件 能够使用的my.cnf配置文件
查看>>
MySQL8.0.29启动报错Different lower_case_table_names settings for server (‘0‘) and data dictionary (‘1‘)
查看>>
MYSQL8.0以上忘记root密码
查看>>
Mysql8.0以上重置初始密码的方法
查看>>
mysql8.0新特性-自增变量的持久化
查看>>
Mysql8.0注意url变更写法
查看>>
Mysql8.0的特性
查看>>
MySQL8修改密码报错ERROR 1819 (HY000): Your password does not satisfy the current policy requirements
查看>>
MySQL8修改密码的方法
查看>>
Mysql8在Centos上安装后忘记root密码如何重新设置
查看>>
Mysql8在Windows上离线安装时忘记root密码
查看>>
MySQL8找不到my.ini配置文件以及报sql_mode=only_full_group_by解决方案
查看>>
mysql8的安装与卸载
查看>>
MySQL8,体验不一样的安装方式!
查看>>