mirror of
https://github.com/opencv/opencv.git
synced 2024-12-24 17:18:28 +08:00
143 lines
9.8 KiB
ReStructuredText
143 lines
9.8 KiB
ReStructuredText
Cascade Classification
|
|
======================
|
|
|
|
.. highlight:: cpp
|
|
|
|
Haar Feature-based Cascade Classifier for Object Detection
|
|
----------------------------------------------------------
|
|
|
|
The object detector described below has been initially proposed by Paul Viola [Viola01]_ and improved by Rainer Lienhart [Lienhart02]_.
|
|
|
|
First, a classifier (namely a *cascade of boosted classifiers working with haar-like features*) is trained with a few hundred sample views of a particular object (i.e., a face or a car), called positive examples, that are scaled to the same size (say, 20x20), and negative examples - arbitrary images of the same size.
|
|
|
|
After a classifier is trained, it can be applied to a region of interest (of the same size as used during the training) in an input image. The classifier outputs a "1" if the region is likely to show the object (i.e., face/car), and "0" otherwise. To search for the object in the whole image one can move the search window across the image and check every location using the classifier. The classifier is designed so that it can be easily "resized" in order to be able to find the objects of interest at different sizes, which is more efficient than resizing the image itself. So, to find an object of an unknown size in the image the scan procedure should be done several times at different scales.
|
|
|
|
The word "cascade" in the classifier name means that the resultant classifier consists of several simpler classifiers (*stages*) that are applied subsequently to a region of interest until at some stage the candidate is rejected or all the stages are passed. The word "boosted" means that the classifiers at every stage of the cascade are complex themselves and they are built out of basic classifiers using one of four different ``boosting`` techniques (weighted voting). Currently Discrete Adaboost, Real Adaboost, Gentle Adaboost and Logitboost are supported. The basic classifiers are decision-tree classifiers with at least 2 leaves. Haar-like features are the input to the basic classifiers, and are calculated as described below. The current algorithm uses the following Haar-like features:
|
|
|
|
|
|
.. image:: pics/haarfeatures.png
|
|
|
|
|
|
The feature used in a particular classifier is specified by its shape (1a, 2b etc.), position within the region of interest and the scale (this scale is not the same as the scale used at the detection stage, though these two scales are multiplied). For example, in the case of the third line feature (2c) the response is calculated as the difference between the sum of image pixels under the rectangle covering the whole feature (including the two white stripes and the black stripe in the middle) and the sum of the image pixels under the black stripe multiplied by 3 in order to compensate for the differences in the size of areas. The sums of pixel values over a rectangular regions are calculated rapidly using integral images (see below and the :ocv:func:`integral` description).
|
|
|
|
To see the object detector at work, have a look at the facedetect demo:
|
|
https://github.com/Itseez/opencv/tree/master/samples/cpp/dbt_face_detection.cpp
|
|
|
|
The following reference is for the detection part only. There is a separate application called ``opencv_traincascade`` that can train a cascade of boosted classifiers from a set of samples.
|
|
|
|
.. note:: In the new C++ interface it is also possible to use LBP (local binary pattern) features in addition to Haar-like features.
|
|
|
|
.. [Viola01] Paul Viola and Michael J. Jones. Rapid Object Detection using a Boosted Cascade of Simple Features. IEEE CVPR, 2001. The paper is available online at http://research.microsoft.com/en-us/um/people/viola/Pubs/Detect/violaJones_CVPR2001.pdf
|
|
|
|
.. [Lienhart02] Rainer Lienhart and Jochen Maydt. An Extended Set of Haar-like Features for Rapid Object Detection. IEEE ICIP 2002, Vol. 1, pp. 900-903, Sep. 2002. This paper, as well as the extended technical report, can be retrieved at http://www.multimedia-computing.de/mediawiki//images/5/52/MRL-TR-May02-revised-Dec02.pdf
|
|
|
|
|
|
CascadeClassifier
|
|
-----------------
|
|
.. ocv:class:: CascadeClassifier
|
|
|
|
Cascade classifier class for object detection.
|
|
|
|
CascadeClassifier::CascadeClassifier
|
|
----------------------------------------
|
|
Loads a classifier from a file.
|
|
|
|
.. ocv:function:: CascadeClassifier::CascadeClassifier(const String& filename)
|
|
|
|
.. ocv:pyfunction:: cv2.CascadeClassifier([filename]) -> <CascadeClassifier object>
|
|
|
|
:param filename: Name of the file from which the classifier is loaded.
|
|
|
|
|
|
|
|
CascadeClassifier::empty
|
|
----------------------------
|
|
Checks whether the classifier has been loaded.
|
|
|
|
.. ocv:function:: bool CascadeClassifier::empty() const
|
|
|
|
|
|
.. ocv:pyfunction:: cv2.CascadeClassifier.empty() -> retval
|
|
|
|
CascadeClassifier::load
|
|
---------------------------
|
|
Loads a classifier from a file.
|
|
|
|
.. ocv:function:: bool CascadeClassifier::load(const String& filename)
|
|
|
|
.. ocv:pyfunction:: cv2.CascadeClassifier.load(filename) -> retval
|
|
|
|
:param 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.
|
|
|
|
|
|
|
|
CascadeClassifier::read
|
|
---------------------------
|
|
Reads a classifier from a FileStorage node.
|
|
|
|
.. ocv:function:: bool CascadeClassifier::read(const FileNode& node)
|
|
|
|
.. note:: The file may contain a new cascade classifier (trained traincascade application) only.
|
|
|
|
|
|
CascadeClassifier::detectMultiScale
|
|
---------------------------------------
|
|
Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles.
|
|
|
|
.. ocv:function:: void CascadeClassifier::detectMultiScale( InputArray image, vector<Rect>& objects, double scaleFactor=1.1, int minNeighbors=3, int flags=0, Size minSize=Size(), Size maxSize=Size())
|
|
.. ocv:function:: void CascadeClassifier::detectMultiScale( InputArray image, vector<Rect>& objects, vector<int>& numDetections, double scaleFactor=1.1, int minNeighbors=3, int flags=0, Size minSize=Size(), Size maxSize=Size())
|
|
.. ocv:function:: void CascadeClassifier::detectMultiScale( InputArray image, std::vector<Rect>& objects, std::vector<int>& rejectLevels, std::vector<double>& levelWeights, double scaleFactor = 1.1, int minNeighbors = 3, int flags = 0, Size minSize = Size(), Size maxSize = Size(), bool outputRejectLevels = false )
|
|
|
|
.. ocv:pyfunction:: cv2.CascadeClassifier.detectMultiScale(image[, scaleFactor[, minNeighbors[, flags[, minSize[, maxSize]]]]]) -> objects
|
|
.. ocv:pyfunction:: cv2.CascadeClassifier.detectMultiScale2(image[, scaleFactor[, minNeighbors[, flags[, minSize[, maxSize]]]]]) -> objects, numDetections
|
|
.. ocv:pyfunction:: cv2.CascadeClassifier.detectMultiScale3(image[, scaleFactor[, minNeighbors[, flags[, minSize[, maxSize[, outputRejectLevels]]]]]]) -> objects, rejectLevels, levelWeights
|
|
|
|
.. ocv:cfunction:: CvSeq* cvHaarDetectObjects( const CvArr* image, CvHaarClassifierCascade* cascade, CvMemStorage* storage, double scale_factor=1.1, int min_neighbors=3, int flags=0, CvSize min_size=cvSize(0,0), CvSize max_size=cvSize(0,0) )
|
|
|
|
:param cascade: Haar classifier cascade (OpenCV 1.x API only). It can be loaded from XML or YAML file using :ocv:cfunc:`Load`. When the cascade is not needed anymore, release it using ``cvReleaseHaarClassifierCascade(&cascade)``.
|
|
|
|
:param image: Matrix of the type ``CV_8U`` containing an image where objects are detected.
|
|
|
|
:param objects: Vector of rectangles where each rectangle contains the detected object, the rectangles may be partially outside the original image.
|
|
|
|
:param 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.
|
|
|
|
:param scaleFactor: Parameter specifying how much the image size is reduced at each image scale.
|
|
|
|
:param minNeighbors: Parameter specifying how many neighbors each candidate rectangle should have to retain it.
|
|
|
|
:param flags: Parameter with the same meaning for an old cascade as in the function ``cvHaarDetectObjects``. It is not used for a new cascade.
|
|
|
|
:param minSize: Minimum possible object size. Objects smaller than that are ignored.
|
|
|
|
:param maxSize: Maximum possible object size. Objects larger than that are ignored.
|
|
|
|
:param outputRejectLevels: Boolean. If ``True``, it returns the rejectLevels and levelWeights. Default value is ``False``.
|
|
|
|
The function is parallelized with the TBB library.
|
|
|
|
.. note::
|
|
|
|
* (Python) A face detection example using cascade classifiers can be found at opencv_source_code/samples/python2/facedetect.py
|
|
|
|
|
|
groupRectangles
|
|
-------------------
|
|
Groups the object candidate rectangles.
|
|
|
|
.. ocv:function:: void groupRectangles(vector<Rect>& rectList, int groupThreshold, double eps=0.2)
|
|
.. ocv:function:: void groupRectangles(vector<Rect>& rectList, vector<int>& weights, int groupThreshold, double eps=0.2)
|
|
|
|
.. ocv:pyfunction:: cv2.groupRectangles(rectList, groupThreshold[, eps]) -> rectList, weights
|
|
|
|
|
|
:param rectList: Input/output vector of rectangles. Output vector includes retained and grouped rectangles. (The Python list is not modified in place.)
|
|
|
|
:param groupThreshold: Minimum possible number of rectangles minus 1. The threshold is used in a group of rectangles to retain it.
|
|
|
|
:param eps: Relative difference between sides of the rectangles to merge them into a group.
|
|
|
|
The function is a wrapper for the generic function
|
|
:ocv:func:`partition` . It clusters all the input rectangles using the rectangle equivalence criteria that combines rectangles with similar sizes and similar locations. The similarity is defined by ``eps``. When ``eps=0`` , no clustering is done at all. If
|
|
:math:`\texttt{eps}\rightarrow +\inf` , all the rectangles are put in one cluster. Then, the small clusters containing less than or equal to ``groupThreshold`` rectangles are rejected. In each other cluster, the average rectangle is computed and put into the output rectangle list.
|