Class HaarCascade

Namespace

Bonsai.Vision

Assembly

Bonsai.Vision.dll

Represents an operator that detects objects on each image in the sequence using a pre-trained cascade of boosted Haar classifiers.

public class HaarCascade : Transform<IplImage, Rect[]>

Inheritance

object

Combinator<IplImage, Rect[]>

Transform<IplImage, Rect[]>

HaarCascade

Inherited Members

Combinator<IplImage, Rect[]>.Process(IObservable<IplImage>)

object.ToString()

object.Equals(object)

object.Equals(object, object)

object.ReferenceEquals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

Properties

FileName

Gets or sets the name of the file describing a trained Haar cascade classifier.

[FileNameFilter("XML Files|*.xml|All Files|*.*")]
public string FileName { get; set; }

Property Value

string

Flags

Gets or sets a value specifying the optional operation flags for the Haar cascade classifier.

public HaarDetectObjectFlags Flags { get; set; }

Property Value

HaarDetectObjectFlags

MaxSize

Gets or sets the optional maximum window size. By default, it is set to the total image size.

public Size MaxSize { get; set; }

Property Value

Size

MinNeighbors

Gets or sets the minimum number (minus 1) of neighbor rectangles that make up an object. All groups with smaller number of rectangles are rejected.

public int MinNeighbors { get; set; }

Property Value

int

MinSize

Gets or sets the optional minimum window size. By default, it is set to the size specified in the cascade classifier file.

public Size MinSize { get; set; }

Property Value

Size

Offset

Gets or sets the optional offset to apply to individual object rectangles.

public Point Offset { get; set; }

Property Value

Point

ScaleFactor

Gets or sets the factor by which the search window is scaled between subsequent scans.

public double ScaleFactor { get; set; }

Property Value

double

Methods

Process(IObservable<IplImage>)

Detects objects on each image in an observable sequence using a pre-trained cascade of boosted Haar classifiers.

public override IObservable<Rect[]> Process(IObservable<IplImage> source)

Parameters

source IObservable<IplImage>

The sequence of images on which to detect objects using the boosted Haar classifier cascade.

Returns

IObservable<Rect[]>

A sequence of Rect arrays representing the objects which were detected on each image of the source sequence.