1. Une brève introduction avec des exemples.
OpenCV
Une brève introduction avec des exemples.

2. Sommaire 1. Introduction
2. Structure de base de OpenCV : The Core      Functionality      < ,      
     (CV::Mat) –classe foindamentale pour représentation des images et des images vidéo    *differents types de codage (RGB, Grey, RGB= alpha -- structure de      données)  HighGUI : gestion des image, affichage, lecture ,-ecriture       High-level GUI and Media I/O      <    4.  Traitements d'images et videos modes et algorithmes pour les applications de mobilité

3. Introduction
OpenCV (pour Open Computer Vision) est une bibliothèque graphique libre, initialement développée par Intel, spécialisée dans le traitement d'images en temps réel.
Elle peut être utilisée dans une application Android en grâce au jni (Java Native Interface).

4. 26/10/11

5. Introduction Pourquoi?
Téléphon eMobile : outil de communication multimédia :
Prendre des photos bien focalisées,
Envoyer les vidéos : « citizen reporteur » - BBC, BFMTV, sécurité : MotionCam,
Filtrer l’information personnelle,
Consulter les BD images

6. Filtrage de l’information personnelle
26/10/11

7. Structure de base de OpenCV
OpenCV 2.x is a C++ library as opposed to OpenCV 1.x
Significant changes in module structure since version 2.2
Modules: core, imgproc, video, calib3d, features2d, objdetect, highgui, gpu...

8. OpenCV core functionality
All the OpenCV classes and functions are placed into the cv namespace
core - compact module defining basic data structures and basic functions used by all other modules
Basic image class cv::Mat
26/10/11

9. cv::Mat memory management
OpenCV handles all the memory automatically
Memory is freed automatically when needed
When a Mat instance is copied, no actual data is really copied
To make a real copy, use Mat::clone
26/10/11

10. The Mat class I cv::Mat covers the old CvMat and IplImage
Data representation
Data is row ordered
Colour pixels are interleaved (e. g. RGBRGBRGB...)
Let's see some important members of the class:
Create and initialize
// Mat(int _rows, int _cols, int _type);
// Mat(Size _size, int _type); type = CV_8UC3, CV_32FC1, ...
// Mat(Size _size, int _type, const Scalar& _s); fill with values in _s
Mat M(7,7,CV_32FC2,Scalar(1,3));//7x7, float, 2 channels, fill with (1,3)
M.create(Size(15,15), CV_8U);//reallocate (if needed)
//Matlab-like initializers
Mat ident = Mat::eye(3,3, CV_32F);//also Mat::ones(..) and Mat::zeros(..)
int* data = {1,2,3,9,0,-3};
Mat C (2,3,CV_32S, data); //no data copied.
C = C.clone(); //clone the matrix -> now the data is created.
26/10/11

11. The Mat class II Important things to know:
Shallow copy: Mat A = B; does not copy data.
Deep copy: clone() and/or B.copyTo(A); (for ROIs, etc).
Most OpenCV functions can resize matrices if needed
Lots of convenient functionality (Matrix expressions):
s is a cv::Scalar, α scalar (double)
Addition, scaling, ...: A±B, A±s, s±A, αA
Per-element multiplication, division...: A.mul(B), A/B, α/A
Matrix multiplication, dot, cross product: A*B, A.dot(B),
A.cross(B)
Transposition, inversion: A.t(), A.inv([method])
And a few more.
26/10/11

12. Mat class: element access I
Rows, columns, ROIs,...
Mat A = B.row(int row); //same for B.col()
A = B.rowRange(Range rg);//same for B.colRange()
A = B(Rect r);//use a rectangle to set ROI
Ranges, ROIs, etc... only create new headers.
Where is a ROI in the bigger matrix?
Mat A = B(Rect r);
Size s; Point offset;
A.locateROI(s, offset); //'s' and 'offset' will define the rectangle 'rect'
Element access: 3 options
Using at<>()
double val = M.at<double>(i, j);//You have to know the type
26/10/11

13. Mat class: element access II
Old C style.
// compute sum of positive matrix elements
double sum=0;
for(int i = 0; i < M.rows; i++) {
const double* Mi = M.ptr<double>(i); //we know it's double data
for(int j = 0; j < M.cols; j++)
sum += std::max(Mi[j], 0.); }
STL-like iterators
// compute sum of positive matrix elements, iterator-based variant
MatConstIterator_<double> it = M.begin<double>(), it_end = M.end<double>();
for(; it != it_end; ++it)
sum += std::max(*it, 0.);
This iterators can be used with STL functions, like std::sort()
26/10/11

14. The Mat_ class I
A thin wrap around the Mat class. Mat ↔ Mat_ can be converted freely
With care: no data conversion is done
Type specification is different
Useful if you do lots of element access.
Same internal code, but shorted to write
Mat_<double> M(20,20); //a double matrix 20x20
double k = M(2,18); //no data specification needed
For multichannel (colour images), use cv::Vec
Mat_<Vec3f> M3f(20,20); //a 20x20 3 channel float matrix
26/10/11

15. Image examples Mat_<uchar> (8 bpp) Mat_<Vec3u> (24 bpp)
26/10/11

16. Manipulation with images using Mat class
Reading and writing images is easy
Mat imread(const string& filename, int flags=1);
//flags =0 -> always grayscale
//flags >0 -> always color
//flags <0 -> read image as-is
bool imwrite(const string& filename, const Mat& img,
const vector<int>& params=vector<int>());
//params set compressions values. defaults are fine.
example:
Mat img = imread("filename.jpg", 1);
imwrite("file.png", myImage);
26/10/11

17. Examples: thresholding
#include <cv.h>
#include <highgui.h>
using namespace std;
using namespace cv;
int main( int argc, char** argv ) {
Mat src, gray, grayThresh;
src = imread(argc >= 2 ? argv[1] : "fruits.jpg", 1);
gray.create(src.size(), CV_8U);//not needed, actually
namedWindow("src", CV_WINDOW_AUTOSIZE);
namedWindow("gray", CV_WINDOW_AUTOSIZE);
namedWindow("grayThreshold", CV_WINDOW_AUTOSIZE);
cvtColor(src, gray, CV_BGR2GRAY); //color images are BGR!
threshold(gray, grayThresh, 100, 250, CV_THRESH_BINARY);
imshow("src", src);
imshow("gray", gray);
imshow("grayThreshold", grayThresh);
waitKey(0); //waits for a key: it also handles the GUI events. }
return 0; //no need to free the matrices, they are deleted automatically
26/10/11

18. Examples: Canny edge detector
#include <cv.h>
#include <highgui.h>
using namespace std;
using namespace cv;
int main( int argc, char** argv ) {
Mat src, dst;
src = imread(argc >= 2 ? argv[1] : "fruits.jpg", 0);
// dst = Mat(src.size(), src.type());
Canny(src, dst, 100, 150, 3);
namedWindow("src"); imshow("src", src);
namedWindow("canny"); imshow("canny", dst);
WaitKey(0);
return 0; }
26/10/11

19. HighGUI: Creating Interfaces I
Start off by creating a program that will constantly input images from a camera
#include <cv.h>
#include <highgui.h>
int main() {
CvCapture* capture = 0;
capture = cvCaptureFromCAM(0);
if(!capture)
printf("Could not initialize capturing...\n");
return -1; }
cvNamedWindow("video");
This code creates a capture structure pointing to camera #0 and creates a window named “video”
26/10/11

20. HighGUI: Creating Interfaces II
Create two variables holding the values of the trackbars we’ll create
int bright=128, contrast=26;
And now we actually create the trackbars:
cvCreateTrackbar("brightness", //name of the trackbar
"video", //name of the window
&bright, //pointer to a variable that will hold the value of the trackbar)
255, //maximum value of the trackbar (minimum is always 0)
NULL); //A callback function (which is called whenever the position of the trackbar is changed)
cvCreateTrackbar("contrast", "video", &contrast, 50, NULL);
Start the infinite loop requesting for frames:
while(true) {
IplImage* frame = 0;
frame = cvQueryFrame(capture);
if (!frame)
break;
26/10/11

21. HighGUI: Creating Interfaces III
bright is in range [0,255], thus subtract 128 to have a convenient range to reduce to increase brightness.
Modify image contrast and brightness by adding to every pixel bright value and scaling by contrast
cvAddS(frame, cvScalar(bright-128,bright-128,bright- 128), frame);
Display the image in the window “video” until the Esc key (ASCII = 27) is pressed
cvShowImage("video", frame);
int c = cvWaitKey(20);
if ((char)c==27)
break; }
cvReleaseCapture(&capture);
return 0;
26/10/11

22. HighGUI: trackbar example
26/10/11

23. OpenCV: image filtering
In this tutorial you will learn how to apply diverse linear filters to smooth images using OpenCV functions such as:
Blur
Gaussian blur
Median blur
Bilateral filter
26/10/11

24. Theory Smoothing (blurring) is a simple and frequently used operation
There are many reasons for smoothing, e.g. noise suppression
To perform a smoothing operation we will apply a filter to our image. The most common type of filters are linear, in which an output pixel’s value (i.e. 𝑔(𝑖,𝑗)) is determined as a weighted sum of input pixel values (i.e.  𝑓(𝑖+𝑘,𝑗+𝑙)) :
𝑔 𝑖,𝑗 = 𝑘,𝑙 𝑓 𝑖+𝑘,𝑗+𝑙 ℎ(𝑘,𝑙)
ℎ(𝑘,𝑙) is called the kernel, which is nothing more than the coefficients of the filter.
It helps to visualize a filter as a window of coefficients sliding across the image.
26/10/11

25. Normalized Box Filter
This filter is the simplest of all! Each output pixel is the mean of its kernel neighbors (all of them contribute with equal weights)
The kernel is below:
𝐾= 1 𝐾 𝑤𝑖𝑑𝑡ℎ ∗ 𝐾 ℎ𝑒𝑖𝑔ℎ𝑡 1 … 1 … … … 1 … 1
26/10/11

26. Gaussian Filter I
Probably the most useful filter (although not the fastest). Gaussian filtering is done by convolving each point in the input array with a  Gaussian kernel.
1D Gaussian kernel
26/10/11

27. Gaussian Filter II Pixel located in the middle has the biggest weight.
The weight of its neighbors decreases as the spatial distance between them and the center pixel increases.
2D Gaussian kernel
where 𝜇 is the mean (the peak) and 𝜎 represents the variance (per each of the variables 𝑥 and  𝑦)
26/10/11

28. Median filter
The median filter run through each element of the signal (in this case the image) and replace each pixel with the median of its neighboring pixels (located in a square neighborhood around the evaluated pixel).
The median of a finite list of numbers can be found by arranging all the observations from lowest value to highest value and picking the middle one.
26/10/11

29. Bilateral Filter
Considered filters main goal were to smooth an input image. However, sometimes the filters do not only dissolve the noise, but also smooth away the edges. To avoid this (at certain extent at least), we can use a bilateral filter.
In an analogous way as the Gaussian filter, the bilateral filter also considers the neighboring pixels with weights assigned to each of them.
These weights have two components
The first component is the same weighting used by the Gaussian filter
The second component takes into account the difference in intensity between the neighboring pixels and the evaluated one.
26/10/11

30. Usage examples Box filter
blur(src, dst, Size( filt_size_x, filt_size_y), Point(-1,-1));
src: Source image
dst: Destination image
Size( w,h ): Defines the size of the kernel to be used ( of width w pixels and height h pixels)
Point(-1, -1): Indicates where the anchor point (the pixel evaluated) is located with respect to the neighborhood. If there is a negative value, then the center of the kernel is considered the anchor point.
Gaussian blur
GaussianBlur( src, dst, Size(filt_size_x, filt_size_y ), 0, 0 );
Size(w, h): The size of the kernel to be used (the neighbors to be considered).  and  have to be odd and positive numbers otherwise the size will be calculated using the and  arguments.
sigma_x: The standard deviation in x. Writing 0 implies that  is calculated using kernel size.
sigma_y: The standard deviation in y. Writing 0 implies that  is calculated using kernel size.
26/10/11

31. TD
Détection de visages
Masquage
26/10/11

32. Usage examples II Median blur medianBlur(src, dst, filt_size
src: Source image
dst: Destination image, must be the same type as src
i: Size of the kernel (only one because we use a square window). Must be odd.
Bilateral filter
bilateralFilter ( src, dst, filt_size , filt_size *2, filt_size /2 )
d: The diameter of each pixel neighborhood.
sigma_col: Standard deviation in the color space (pixel values).
sigma: Standard deviation in the coordinate space (in pixels)
26/10/11

33. Median blur example
26/10/11

34. Face detection Slides partly borrowed from
26/10/11

35. Face detection II
Basic idea: slide a window across image and evaluate a face model at every location
Challenges:
Sliding window detector must evaluate tens of thousands of location/scale combinations
Faces are rare: 0–10 per image
For computational efficiency, we should try to spend as little time as possible on the non-face windows
A megapixel image has ~106 pixels and a comparable number of candidate face locations
To avoid having a false positive in every image, our false positive rate has to be less than 10-6
26/10/11

36. Object classification
Takes as input 𝑛-dimensional vector of parameters 𝑣
Training step: given a number of samples of each class and corresponding feature vectors -> builds 𝑛-dimensional space partitioning
Classification: using acquired partitioning, make decision to which class object belongs to based on its feature vector
Feature vector is any reasonable set of parameters that makes good separation of the objects of different class
26/10/11

37. The simplest classifier : thresholding
f(x)
26/10/11

38. The Viola/Jones Face Detector
Training is slow, but detection is very fast
Key ideas
Integral images for fast feature evaluation
Boosting for feature selection
Classifier cascade for fast rejection of non-face windows
P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. CVPR 2001
P. Viola and M. Jones. Robust real-time face detection. IJCV 57(2), 2004.
26/10/11

39. Image Features
Rectangular filters of wearable size in window 24x24 pels
Value = ∑ (pixels in white area) – ∑ (pixels in black area)
Examples of features
26/10/11

40. Example
Source
Result
Value~0
26/10/11
Value >>0

41. Fast computation with integral image
The integral image computes a value at each pixel (x,y) that is the sum of the pixel values above and to the left of (x,y), inclusive
Sum of values inside the rectangle sum = A – B – C + D
(x,y) D B C A
26/10/11

42. Feature selection
For a 24x24 detection region, the number of possible rectangle features is ~160,000!
At detection time, it is impractical to evaluate the entire feature set
Can we create a good classifier using just a small subset of all possible features?
How to select such a subset?
26/10/11

43. Boosting Learn a single simple classifier Classify the data
Look at where it makes errors
Reweight the data so that the inputs where we made errors get higher weight in the learning process
Now learn a 2nd simple classifier on the weighted data
Combine the 1st and 2nd classifier and weight the data
according to where they make errors
Learn a 3rd classifier on the weighted data
Final classifier is the combination of all T classifiers
This procedure is called “Boosting” – works very well in practice
26/10/11

44. Boosting illustration
Weak
Classifier 1
26/10/11

45. Boosting illustration
Weights
Increased

46. Boosting illustration
Weak
Classifier 3

47. Boosting illustration
Final classifier is
a combination of weak classifiers

48. Boosting for face detection
Define weak learners based on rectangle features
Final classifier 𝐻 𝑓𝑖𝑛𝑎𝑙 =𝑠𝑖𝑔𝑛 ( 0.4∙ℎ ∙ ℎ ∙ ℎ )
value of rectangle feature
threshold
window
26/10/11

49. Boosting for face detection
First two features selected by boosting: This feature combination can yield 100% detection rate and 50% false positive rate

50. Boosting for face detection
A 200-feature classifier can yield 95% detection rate and a false positive rate of 1 in 14084
Not good enough!
Receiver operating characteristic (ROC) curve

51. Classifier cascade
We start with simple classifiers which reject many of the negative sub-windows while detecting almost all positive sub-windows
Positive response from the first classifier triggers the evaluation of a second (more complex) classifier, and so on
A negative outcome at any point leads to the immediate rejection of the sub-window
FACE
IMAGE
SUB-WINDOW
Classifier 1 T
Classifier 3 F
NON-FACE
Classifier 2

52. Classifier cascade
A detection rate of 0.9 and a false positive rate on the order of 10-6 can be achieved by a 10-stage cascade if each stage has a detection rate of 0.99 ( ≈ 0.9) and a false positive rate of about 0.30 (0.310 ≈ 6×10-6)
26/10/11

53. Output of Face Detector on Test Images

54. OpenCV face detection
OpenCV already have cascade classifiers and Haar features implemented
Pre-trained cascades for face detection as well as eyes and some more are also included! (Look in "data/haarcascades/ “)
26/10/11

55. Code example
#include <opencv2/objdetect/objdetect.hpp> #include <opencv2/highgui/highgui.hpp> #include <opencv2/imgproc/imgproc.hpp> int main() { CascadeClassifier cascade("../../data/haarcascades/haarcascade_frontalface_alt.xml“); Mat img = imread( "lena.jpg", 1 ); vector<Rect> faces; Mat gray; cvtColor( img, gray, CV_BGR2GRAY ); cascade.detectMultiScale( smallImg, faces, 1.1, 2, 0 /*default optons*/, Size(30, 30) ); for( vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++ ) circle( img, center, radius, color, 3, 8, 0 ); } imshow( "result", img );
26/10/11

56. TD
Détection de visages
Masquage
26/10/11