opencv--feature2d之FeatureDetector

最新推荐文章于 2025-04-03 11:06:49 发布

原创最新推荐文章于 2025-04-03 11:06:49 发布 · 1.6k 阅读

0 ·

本内容遵循CC 4.0 BY-SA版权协议

opencv 同时被 2 个专栏收录

25 篇文章

订阅专栏

c++

8 篇文章

订阅专栏

这篇博客介绍了OpenCV中的FeatureDetector类及其在特征检测中的应用，如FAST, STAR, SIFT, SURF等。同时讲解了BOWImgDescriptorExtractor如何用于图像描述符的计算，涉及关键点检测、描述符提取和SVM分类器在训练与识别过程中的角色。" 106576037,9327294,C++实现最长回文子串,"['字符串算法', '动态规划', '数据结构', 'C++编程']

FaceRecognizer::onInit时直接创建了描述符对象：

descriptor_detector_ = new cv::GridAdaptedFeatureDetector();

descriptor_extractor_ = new cv::SurfDescriptorExtractor;

bowExtractor_ = new cv::BOWImgDescriptorExtractor();

训练过程，首先根据样本图像生成提取描述符。然后使用svm分类器。

1.cvtColor 将原始图像转换为灰度图像。

2.归一化直方图。

3.检测灰度图像的关键点，生成关键点。descriptor_detector_->detect

4.根据关键点，从灰度图像提取描述符。生成提取描述符。descriptor_extractor_->compute

5.将生成的提取描述符作为人的描述符。如果模型中没有描述符则直接赋值，如果已有至少一个则匹配插入。

识别检测过程：根据输入图像生成提取描述符，然后使用SVM进行预测。

FeatureDetector

class FeatureDetector : public Algorithm

Abstract base class for 2D image feature detectors.

class CV_EXPORTS FeatureDetector
{
public:
    virtual ~FeatureDetector();

    void detect( const Mat& image, vector<KeyPoint>& keypoints,
                 const Mat& mask=Mat() ) const;

    void detect( const vector<Mat>& images,
                 vector<vector<KeyPoint> >& keypoints,
                 const vector<Mat>& masks=vector<Mat>() ) const;

    virtual void read(const FileNode&);
    virtual void write(FileStorage&) const;

    static Ptr<FeatureDetector> create( const string& detectorType );

protected:
...
};


    Parameters: 
        detectorType – Feature detector type.
The following detector types are supported:
    "FAST" – FastFeatureDetector
"STAR" – StarFeatureDetector
"SIFT" – SIFT (nonfree module)
"SURF" – SURF (nonfree module)
"ORB" – ORB
"BRISK" – BRISK
"MSER" – MSER
"GFTT" – GoodFeaturesToTrackDetector
"HARRIS" – GoodFeaturesToTrackDetector with Harris detector enabled
"Dense" – DenseFeatureDetector
"SimpleBlob" – SimpleBlobDetector
BOWImgDescriptorExtractor::compute