cv::CascadeClassifier Class Reference

Cascade classifier class for object detection. More...

#include <objdetect.hpp>

Public Member Functions
CV_WRAP	CascadeClassifier ()
CV_WRAP	CascadeClassifier (const String &filename)
	Loads a classifier from a file. More...
	~CascadeClassifier ()
CV_WRAP bool	empty () const
	Checks whether the classifier has been loaded. More...
CV_WRAP bool	load (const String &filename)
	Loads a classifier from a file. More...
CV_WRAP bool	read (const FileNode &node)
	Reads a classifier from a FileStorage node. More...
CV_WRAP void	detectMultiScale (InputArray image, CV_OUT std::vector< Rect > &objects, double scaleFactor=1.1, int minNeighbors=3, int flags=0, Size minSize=Size(), Size maxSize=Size())
	Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles. More...
	CV_WRAP_AS (detectMultiScale2) void detectMultiScale(InputArray image
	CV_WRAP_AS (detectMultiScale3) void detectMultiScale(InputArray image
CV_WRAP bool	isOldFormatCascade () const
CV_WRAP Size	getOriginalWindowSize () const
CV_WRAP int	getFeatureType () const
void *	getOldCascade ()
void	setMaskGenerator (const Ptr< BaseCascadeClassifier::MaskGenerator > &maskGenerator)
Ptr< BaseCascadeClassifier::MaskGenerator >	getMaskGenerator ()

Static Public Member Functions
static CV_WRAP bool	convert (const String &oldcascade, const String &newcascade)

Public Attributes
CV_OUT std::vector< Rect > &	objects
CV_OUT std::vector< Rect > CV_OUT std::vector< int > &	numDetections
CV_OUT std::vector< Rect > CV_OUT std::vector< int > double	scaleFactor =1.1
CV_OUT std::vector< Rect > CV_OUT std::vector< int > double int	minNeighbors =3
CV_OUT std::vector< Rect > CV_OUT std::vector< int > double int int	flags =0
CV_OUT std::vector< Rect > CV_OUT std::vector< int > double int int Size	minSize =Size()
CV_OUT std::vector< Rect > CV_OUT std::vector< int > double int int Size Size	maxSize =Size() )
CV_OUT std::vector< Rect > CV_OUT std::vector< int > &	rejectLevels
CV_OUT std::vector< Rect > CV_OUT std::vector< int > CV_OUT std::vector< double > &	levelWeights
CV_OUT std::vector< Rect > CV_OUT std::vector< int > CV_OUT std::vector< double > double	scaleFactor = 1.1
CV_OUT std::vector< Rect > CV_OUT std::vector< int > CV_OUT std::vector< double > double int	minNeighbors = 3
CV_OUT std::vector< Rect > CV_OUT std::vector< int > CV_OUT std::vector< double > double int int	flags = 0
CV_OUT std::vector< Rect > CV_OUT std::vector< int > CV_OUT std::vector< double > double int int Size	minSize = Size()
CV_OUT std::vector< Rect > CV_OUT std::vector< int > CV_OUT std::vector< double > double int int Size Size	maxSize = Size()
CV_OUT std::vector< Rect > CV_OUT std::vector< int > CV_OUT std::vector< double > double int int Size Size bool	outputRejectLevels = false )
Ptr< BaseCascadeClassifier >	cc

Detailed Description

Cascade classifier class for object detection.

Constructor & Destructor Documentation

CascadeClassifier() [1/2]

CV_WRAP cv::CascadeClassifier::CascadeClassifier

(

)

CascadeClassifier() [2/2]

CV_WRAP cv::CascadeClassifier::CascadeClassifier

(

const String &

filename

)

Loads a classifier from a file.

Parameters

filename

Name of the file from which the classifier is loaded.

~CascadeClassifier()

cv::CascadeClassifier::~CascadeClassifier

(

)

Member Function Documentation

convert()

static CV_WRAP bool cv::CascadeClassifier::convert ( const String &  oldcascade, const String &  newcascade  )

static

CV_WRAP_AS() [1/2]

cv::CascadeClassifier::CV_WRAP_AS

(

detectMultiScale2

)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

image	Matrix of the type CV_8U containing an image where objects are detected.
objects	Vector of rectangles where each rectangle contains the detected object, the rectangles may be partially outside the original image.
numDetections	Vector of detection numbers for the corresponding objects. An object's number of detections is the number of neighboring positively classified rectangles that were joined together to form the object.
scaleFactor	Parameter specifying how much the image size is reduced at each image scale.
minNeighbors	Parameter specifying how many neighbors each candidate rectangle should have to retain it.
flags	Parameter with the same meaning for an old cascade as in the function cvHaarDetectObjects. It is not used for a new cascade.
minSize	Minimum possible object size. Objects smaller than that are ignored.
maxSize	Maximum possible object size. Objects larger than that are ignored. If maxSize == minSize model is evaluated on single scale.

CV_WRAP_AS() [2/2]

cv::CascadeClassifier::CV_WRAP_AS

(

detectMultiScale3

)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. This function allows you to retrieve the final stage decision certainty of classification. For this, one needs to set outputRejectLevels on true and provide the rejectLevels and levelWeights parameter. For each resulting detection, levelWeights will then contain the certainty of classification at the final stage. This value can then be used to separate strong from weaker classifications.

A code sample on how to use it efficiently can be found below:

Mat img;
vector<double> weights;
vector<int> levels;
vector<Rect> detections;
CascadeClassifier model("/path/to/your/model.xml");
model.detectMultiScale(img, detections, levels, weights, 1.1, 3, 0, Size(), Size(), true);
cerr << "Detection " << detections[0] << " with weight " << weights[0] << endl;

detectMultiScale()

CV_WRAP void cv::CascadeClassifier::detectMultiScale	(	InputArray	image,
		CV_OUT std::vector< Rect > &	objects,
		double	scaleFactor = 1.1,
		int	minNeighbors = 3,
		int	flags = 0,
		Size	minSize = Size(),
		Size	maxSize = Size()
	)

Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles.

Parameters

image	Matrix of the type CV_8U containing an image where objects are detected.
objects	Vector of rectangles where each rectangle contains the detected object, the rectangles may be partially outside the original image.
scaleFactor	Parameter specifying how much the image size is reduced at each image scale.
minNeighbors	Parameter specifying how many neighbors each candidate rectangle should have to retain it.
flags	Parameter with the same meaning for an old cascade as in the function cvHaarDetectObjects. It is not used for a new cascade.
minSize	Minimum possible object size. Objects smaller than that are ignored.
maxSize	Maximum possible object size. Objects larger than that are ignored. If maxSize == minSize model is evaluated on single scale.

empty()

CV_WRAP bool cv::CascadeClassifier::empty

(

)

const

Checks whether the classifier has been loaded.

getFeatureType()

CV_WRAP int cv::CascadeClassifier::getFeatureType

(

)

const

getMaskGenerator()

Ptr<BaseCascadeClassifier::MaskGenerator> cv::CascadeClassifier::getMaskGenerator

(

)

getOldCascade()

void* cv::CascadeClassifier::getOldCascade

(

)

getOriginalWindowSize()

CV_WRAP Size cv::CascadeClassifier::getOriginalWindowSize

(

)

const

isOldFormatCascade()

CV_WRAP bool cv::CascadeClassifier::isOldFormatCascade

(

)

const

load()

CV_WRAP bool cv::CascadeClassifier::load

(

const String &

filename

)

Loads a classifier from a file.

Parameters

filename

Name of the file from which the classifier is loaded. The file may contain an old HAAR classifier trained by the haartraining application or a new cascade classifier trained by the traincascade application.

read()

CV_WRAP bool cv::CascadeClassifier::read

(

const FileNode &

node

)

Reads a classifier from a FileStorage node.

Note

The file may contain a new cascade classifier (trained by the traincascade application) only.

setMaskGenerator()

void cv::CascadeClassifier::setMaskGenerator

(

const Ptr< BaseCascadeClassifier::MaskGenerator > &

maskGenerator

)

Member Data Documentation

cc

Ptr<BaseCascadeClassifier> cv::CascadeClassifier::cc

flags [1/2]

CV_OUT std::vector<Rect> CV_OUT std::vector<int> double int int cv::CascadeClassifier::flags =0

flags [2/2]

CV_OUT std::vector<Rect> CV_OUT std::vector<int> CV_OUT std::vector<double> double int int cv::CascadeClassifier::flags = 0

levelWeights

CV_OUT std::vector<Rect> CV_OUT std::vector<int> CV_OUT std::vector<double>& cv::CascadeClassifier::levelWeights

maxSize [1/2]

CV_OUT std::vector<Rect> CV_OUT std::vector<int> double int int Size Size cv::CascadeClassifier::maxSize =Size() )

maxSize [2/2]

CV_OUT std::vector<Rect> CV_OUT std::vector<int> CV_OUT std::vector<double> double int int Size Size cv::CascadeClassifier::maxSize = Size()

minNeighbors [1/2]

CV_OUT std::vector<Rect> CV_OUT std::vector<int> double int cv::CascadeClassifier::minNeighbors =3

minNeighbors [2/2]

CV_OUT std::vector<Rect> CV_OUT std::vector<int> CV_OUT std::vector<double> double int cv::CascadeClassifier::minNeighbors = 3

minSize [1/2]

CV_OUT std::vector<Rect> CV_OUT std::vector<int> double int int Size cv::CascadeClassifier::minSize =Size()

minSize [2/2]

CV_OUT std::vector<Rect> CV_OUT std::vector<int> CV_OUT std::vector<double> double int int Size cv::CascadeClassifier::minSize = Size()

numDetections

CV_OUT std::vector<Rect> CV_OUT std::vector<int>& cv::CascadeClassifier::numDetections

objects

CV_OUT std::vector< Rect > & cv::CascadeClassifier::objects

outputRejectLevels

CV_OUT std::vector<Rect> CV_OUT std::vector<int> CV_OUT std::vector<double> double int int Size Size bool cv::CascadeClassifier::outputRejectLevels = false )

rejectLevels

CV_OUT std::vector<Rect> CV_OUT std::vector<int>& cv::CascadeClassifier::rejectLevels

scaleFactor [1/2]

CV_OUT std::vector<Rect> CV_OUT std::vector<int> double cv::CascadeClassifier::scaleFactor =1.1

scaleFactor [2/2]

CV_OUT std::vector<Rect> CV_OUT std::vector<int> CV_OUT std::vector<double> double cv::CascadeClassifier::scaleFactor = 1.1

---

The documentation for this class was generated from the following file:

• build/release/_deps/opencv-src/include/opencv4/opencv2/objdetect.hpp