Please can some expert person explain me whether we can use the cvHaarDetectObjects() method to detect squares and get width and heights? I found a code that use this method for face-detection but I need to know whether I can use it for rectangle detection.
String src="src/squiredetection/MY.JPG";
IplImage grabbedImage = cvLoadImage(src);
IplImage grayImage = IplImage.create(grabbedImage.width(), grabbedImage.height(), IPL_DEPTH_8U, 1);
cvCvtColor(grabbedImage, grayImage, CV_BGR2GRAY);
CvSeq faces = cvHaarDetectObjects(grayImage, cascade, storage, 1.1, 3, 0);//*
for (int i = 0; i < faces.total(); i++) {
CvRect r = new CvRect(cvGetSeqElem(faces, i));
cvRectangle(grabbedImage, cvPoint(r.x(), r.y()), cvPoint(r.x()+r.width(), r.y()+r.height()), CvScalar.RED, 1, CV_AA, 0);
/* hatPoints[0].x = r.x-r.width/10; hatPoints[0].y = r.y-r.height/10;
hatPoints[1].x = r.x+r.width*11/10; hatPoints[1].y = r.y-r.height/10;
hatPoints[2].x = r.x+r.width/2; hatPoints[2].y = r.y-r.height/2;*/
// cvFillConvexPoly(grabbedImage, hatPoints, hatPoints.length, CvScalar.GREEN, CV_AA, 0);
}
when I use above method it throws following exception
OpenCV Error: Bad argument (Invalid classifier cascade) in unknown function, file C:\slave\WinInstallerMegaPack\src\opencv\modules\objdetect\src\haar.cpp, line 1036
Exception in thread "main" java.lang.RuntimeException: C:\slave\WinInstallerMegaPack\src\opencv\modules\objdetect\src\haar.cpp:1036: error: (-5) Invalid classifier cascade
at com.googlecode.javacv.cpp.opencv_objdetect.cvHaarDetectObjects(Native Method)
at com.googlecode.javacv.cpp.opencv_objdetect.cvHaarDetectObjects(opencv_objdetect.java:243)
at squiredetection.Test2.main(Test2.java:52 I have put * on this line)
Please be kind enough to give simple code example for that.
cvHaarDetectObjects() is used for detecting objects or shapes not only for faces, it depends on HaarCascade classifier.
If you pass face haarcascade xml then it will return an array of faces or also can use eye, nose, etc HaarCascade XML file. You can make also custom haarcascade xml by creating your own positive and negative samples using opencv_traincascade.exe
CvSeq faces = cvHaarDetectObjects(grayImage, classifier, storage,
1.1, 3, CV_HAAR_DO_CANNY_PRUNING);
for (int i = 0; i < faces.total(); i++) {
// its ok
}
detail on opencv doc
for rectangle detection :
there is an example for rectangle detection in OpenCV, they use it to detect
the squares in a chessboard. Have a look to squares.c in
..\OpenCV\samples\c\ directory.
see this chessboard detection sample in opencv
Invalid classifier cascade in unknown function error means the classifier you passed is not correctly formatted or something is missing. Check if your classifier xml file is valid.
cvHaarDetectObjects returns multiple faces detected in an image. You have to declare an array of CvSeq to store the result, not just a single CvSeq.
// There can be more than one face in an image.
// So create a growable sequence of faces.
// Detect the objects and store them in the sequence
CvSeq* faces = cvHaarDetectObjects( img, cascade, storage,
1.1, 2, CV_HAAR_DO_CANNY_PRUNING,
cvSize(40, 40) );
The code above was extracted from this site:
http://opencv.willowgarage.com/wiki/FaceDetection
Related
I am using OpenGL ES 3.2 and the NVIDIA driver 361.00 on a Pixel C tablet with Tegra X1 GPU. I would like to use a compute shader to write data to a colour map and then later I will use some graphics shaders to display the image.
I already have this concept working using desktop GL and now I want to port to mobile. I am implementing the GL in Java rather than in native code. I extend GLSurfaceView and the GLSurfaceView.Renderer and then during the OnSurfaceCreated callback I initialise the shader programs and textures etc.
The compute shader compiles just fine without any errors:
#version 310 es
layout(binding = 0, rgba32f) uniform highp image2D colourMap;
layout(local_size_x = 128, local_size_y = 1, local_size_z = 1) in;
void main()
{
imageStore(colourMap, ivec2(gl_GlobalInvocationID.xy), vec4(1.0f, 0.0f, 0.0f, 1.0f));
}
And I initialise a texture
// Generate a 2D texture
GLES31.glGenTextures(1, colourMap, 0);
GLES31.glBindTexture(GLES31.GL_TEXTURE_2D, colourMap[0]);
// Set interpolation to nearest
GLES31.glTexParameteri(GLES31.GL_TEXTURE_2D, GLES31.GL_TEXTURE_MAG_FILTER, GLES31.GL_LINEAR);
GLES31.glTexParameteri(GLES31.GL_TEXTURE_2D, GLES31.GL_TEXTURE_MIN_FILTER, GLES31.GL_LINEAR);
// Create some dummy texture to begin with so we can see if it changes
float texData[] = new float[texWidth * texHeight * 4];
for (int j = 0; j < texHeight; j++)
{
for (int i = 0; i < texWidth; i++)
{
// Set a few pixels in here...
}
}
Buffer texDataBuffer = FloatBuffer.wrap(texData);
GLES31.glTexImage2D(GLES31.GL_TEXTURE_2D, 0, GLES31.GL_RGBA32F, texWidth, texHeight, 0, GLES31.GL_RGBA, GLES31.GL_FLOAT, texDataBuffer);
After this I set the image unit in the shader here: EDIT: I don't do this now but just assume it will be assigned automatically when the shader program is created as per solidpixel's answer.
GLES31.glUseProgram(idComputeShaderProgram);
int loc = GLES31.glGetUniformLocation(idComputeShaderProgram, "colourMap");
if (loc == -1) Log.e("Error", "Cannot locate variable");
GLES31.glUniform1i(loc, 0);
After every call to GL I check for errors using GLES31.glGetError() -- left out here for clarity.
EDIT: When I dispatch compute I bind the image texture but first query the unit assignment:
GLES31.glUseProgram(idComputeShaderProgram);
int[] unit = new int[1];
GLES31.glGetUniformiv(idComputeShaderProgram, GLES31.glGetUniformLocation(idComputeShaderProgram, "colourMap"), unit, 0);
GLES31.glBindImageTexture(unit[0], velocityMap[0], 0, false, 0, GLES31.GL_WRITE_ONLY, GLES31.GL_RGBA32F);
This final line is the one which errors now. The error code translates to GL_INVALID_OPERATION. The shader compiles correctly and the program object is valid and active. The location of the variable is also valid. I have even used glGetActiveUniform() to get the type of the variable and it returns a type of 36941 which translates to GL_IMAGE_2D which I believe is an integer.
I still think I'm misunderstanding something here but not sure what.
You can't assign your own unit identities for images. See OpenGL ES 3.2 specification section 7.6.
An INVALID_OPERATION error is generated if any of the following
conditions occur:
an image uniform is loaded with any of the Uniform* commands.
You need to query the automatic unit assignment using glGetUniformiv(prog, loc, &unit) to get the unit name.
I'm working on android app, which determines which font is used on a text image. So I need to extract every character from image and don't know how to do it precisely. Furthermore, when I'm trying to process an image I have one result...but my classmate has different (for example, more or less noise). The problem with character detection is that:
1) it detects also some noise blobs on image and shows it in rectangles (I thought about detectMultiScale... but I have doubts about it, maybe there are easiest ways to detect characters)
2) it detects several contours of one character (for example inner and outer radius of letter "o")
And question for the future: I'm going to create a DB with images (for now just 3 fonts) of different letters of fonts and compare them with an image of letters from photo. Maybe someone could recommend a better way to do it.
So this is part of code with image processing(I'm still playing with values of blur, threshold and Canny... but there was no really positive result):
Imgproc.cvtColor(sImage, grayImage, Imgproc.COLOR_BGR2GRAY); //градации серого
Imgproc.GaussianBlur(grayImage,blurImage,new Size(5, 5),0); //размытие
Imgproc.adaptiveThreshold(blurImage, thresImage, 255, Imgproc.ADAPTIVE_THRESH_MEAN_C, Imgproc.THRESH_BINARY, 101, 39);
List<MatOfPoint> contours = new ArrayList<MatOfPoint>();
Mat hierarchy = new Mat();
Imgproc.Canny(thresImage, binImage, 30, 10, 3, true); //контур
Imgproc.findContours(binImage, contours, hierarchy, Imgproc.RETR_TREE, Imgproc.CHAIN_APPROX_SIMPLE, new Point(0, 0));
hierarchy.release();
Imgproc.drawContours(binImage, contours, -1, new Scalar(255, 255, 255));//, 2, 8, hierarchy, 0, new Point());
MatOfPoint2f approxCurve = new MatOfPoint2f();
//For each contour found
for (int i = 0; i < contours.size(); i++) {
//Convert contours(i) from MatOfPoint to MatOfPoint2f
MatOfPoint2f contour2f = new MatOfPoint2f(contours.get(i).toArray());
//Processing on mMOP2f1 which is in type MatOfPoint2f
double approxDistance = Imgproc.arcLength(contour2f, true) * 0.02;
Imgproc.approxPolyDP(contour2f, approxCurve, approxDistance, true);
//Convert back to MatOfPoint
MatOfPoint points = new MatOfPoint(approxCurve.toArray());
// Get bounding rect of contour
Rect rect = Imgproc.boundingRect(points);
// draw enclosing rectangle (all same color, but you could use variable i to make them unique)
Imgproc.rectangle(binImage, new Point(rect.x, rect.y), new Point(rect.x + rect.width, rect.y + rect.height), new Scalar(255, 255, 255), 5);
}
And screen (not actually with processing values from code, just one with better results):
Original:
(unfortunately, I can't add more than 2 links to show more examples)
There were situations, when picture from this screen looked pretty good, but another pictures looked like with shapeless blobs.
Your code is fine, you just need to make a minor tweaks to get it work properly.
Firstly, the image size is very large, you can safely reduce it to 20% of current size without suffering a major loss in accuracy. Due to larger image size all the functions would perform slower.
You dont need to perform adaptive threshold before Canny, canny works perfectly on gray-scale images as well, You need to adjust the params as:
Canny(img, threshold1=170, threshold2=250)
which yields an image as:
[Optional] If you want to de-noise the image then you can try with morphological operations like erode and dilate.
Now you are ready to find the contours. The mistake in your code was using Imgproc.RETR_TREE flag you need to use Imgproc.RETR_EXTERNAL flag to get only the outer contours and not the nested inner contours.
At this step you may have some unwanted small contours, which can be filtered as:
// ** Below code if for reference purposes only, consult OpenCV docs for proper API methods
int character_area_lower_thresh = 10;
for (Contour c:contours) {
if (Imgproc.contourArea(c) > character_area_lower_thresh) {
// Desired contour, do what ever you want to do
Rect r = Imgproc.boundingRect(c);
}
}
I'm trying to use the JavaCV implementation of the HoughCircles method, but I'm having some issues with the parameters.
Here is my code:
Mat currentImageGray = tgtFrag.getImage().clone();
Mat detectedCircles = new Mat();
HoughCircles(currentImageGray, detectedCircles, CV_HOUGH_GRADIENT, 1, 2, 254, 25, tgtFrag.getImage().rows() / 4, 0 );
if (detectedCircles != null && !detectedCircles.empty()) {
// TO DO:
// Print the center and the raidus of the detected circles.
}
First of all, the results of the detection (second argment of the HoughCircles) are given as a Mat (detectedCircles).
I'd like to process the detectedCircles Mat and somehow print the center and the radius of the circle on the console. My attempts have failed so far: I've been trying to iterate detectedCircles using a FloatBufferIndexer, could be the right direction, but I didn't succeed yet, anyone can help?
Please notice the following:
I'm using JavaCV, not openCV.
I'm using JavaCV HoughCircles, not cvHoughCircles (a solution using cvHoughCircles would be also ok though).
I'm using the latest version of JavaCV, i.e. 1.0 (July 2015).
I've only been able to use the JavaCV cvHoughCircles method, no idea about how to use the HoughCircles method though. Here is my adaptation of your code.
// Get the source Mat.
Mat myImage = tgtFrag.getImage();
IplImage currentImageGray = new IplImage(myImage);
CvMemStorage mStorage = CvMemStorage.create();
CvSeq detectedCircles = cvHoughCircles(currentImageGray, mStorage, CV_HOUGH_GRADIENT, 1, 2, 254, 25, tgtFrag.getImage().rows() / 4, 0);
if (detectedCircles != null && detectedCircles.total() > 0) {
for (int i = 0; i < detectedCircles.total(); i++) {
CvPoint3D32f curCircle = new CvPoint3D32f(cvGetSeqElem(detectedCircles, i));
int curRadius = Math.round(curCircle.z());
Point curCenter = new Point(Math.round(curCircle.x()), Math.round(curCircle.y()));
System.out.println(curCenter);
System.out.println(curRadius);
}
}
Even though this does not directly solve your problem, I hope this may help.
I am using Xuggle to play interlaced video from ip-camera and really need in deinterlace option, which exists in FFMpeg (Xuggle is a java wrapper over FFMpeg library).
Unfortunately, deinterlace option ("-vf yadif", if i'm not mistake) is not exposed by Xuggle. So, i'm interested in either pure java solution of Java BufferedImage deinterlacing or some way to make Xuggle do that.
Now i simply duplicate odd lines and discard even. It is quick but quality of course is not very well.
// Interlaced image
BufferedImage img = (BufferedImage) event.getImage();
//duplicate odd lines
WritableRaster raster = img.getRaster();
for (int i = 0; i < raster.getHeight(); i += 2) {
int[] arr2 = null;
raster.setPixels(0, i + 1, raster.getWidth(), 1,
raster.getPixels(0, i, raster.getWidth(), 1,arr2));
}
//now img is deinterlaced
Could somebody help me in this regard?
I used FFMPEG's yadif filter through JNI. Java realisations were very slow.
I'm trying to detect the positions of billiards balls on a table from an image taken at a perspective angle. I'm using the getPerspectiveTransform() method to find the transformation matrix and I want to apply that to only the circles I detect using HoughCircles. I'm trying to go from a rather large trapezoidal shape to a smaller rectangular shape. I don't want to do the transformation on the image first and then find the HoughCircles because the image gets too warped for houghcircles to provide useful results.
Here's my code:
CvMat mmat = cvCreateMat(3,3,CV_32FC1);
double srcX1 = 462;
double srcX2 = 978;
double srcX3 = 1440;
double srcX4 = 0;
double srcY = 241;
double srcHeight = 772;
double dstX = 56.8;
double dstY = 33.5;
double dstWidth = 262.4;
double dstHeight = 447.3;
CvSeq seq = cvHoughCircles(newGray, circles, CV_HOUGH_GRADIENT, 2.1d, (double)newGray.height()/40, 85d, 65d, 5, 50);
JavaCV.getPerspectiveTransform(new double[]{srcX1, srcY, srcX2,srcY, srcX3, srcHeight, srcX4, srcHeight},
new double[]{dstX, dstY, dstWidth, dstY, dstWidth, dstHeight, dstX, dstHeight}, mmat);
cvWarpPerspective(seq, seq, mmat);
for(int j=0; j<seq.total(); j++){
CvPoint3D32f point = new CvPoint3D32f(cvGetSeqElem(seq, j));
float xyr[] = {point.x(),point.y(),point.z()};
CvPoint center = new CvPoint(Math.round(xyr[0]), Math.round(xyr[1]));
int radius = Math.round(xyr[2]);
cvCircle(gray, center, 3, CvScalar.GREEN, -1, 8, 0);
cvCircle(gray, center, radius, CvScalar.BLUE, 3, 8, 0);
}
The problem is I get this error on the warpPerspective() method:
error: (-215) seq->total > 0 && CV_ELEM_SIZE(seq->flags) == seq->elem_size in function cv::Mat cv::cvarrToMat(const CvArr*, bool, bool, int)
Also I guess it's worth mentioning that I'm using JavaCV, in case the method calls look a bit different than what you're used to. Thanks for any help.
Answer:
the problem with what you want to do (besides the obvious, opencv wont let you) is that the radius cant really be warped correctly. AFAIK the xy coordinates are pretty easy to calculate x'=((m00x+m01y+m02)/(m20x+m21y+m22)) y'=((m10x+m11y+m12)/(m20x+m21y_m22)) when m is the transformation matrix. the radius you can hack by transforming all the points of the original circle and then find the max distance between x'y' and those points (atleast if the radius in the warped image is expected to cover all those points)
btw, mIJx = m(i,j)*x (just to clarify)
End Answer.
Everything i write is according to the c++ version, i've never used JavaCV but from what i could see its just a wrapper that calls the native c++ lib.
CvSeq is a sequance data structure that behaves like a linked list.
the assert your application crushes at is
CV_Assert(seq->total > 0 && CV_ELEM_SIZE(seq->flags) == seq->elem_size);
which means that either your seq instance is empty (total is the number of elements in the sequence) or somehow the inner seq flags are corrupted.
I'd recommend that you'd check the total member of your CvSeq, and the cvHoughCircles call.
all of this occurs before the actual implementation of cvWarpPerspective (its the first line in the implementation, that only converts your CvSeq to cv::Mat).. so its not the warping but what you're doing before that.
anyway, to understand whats wrong with cvHoughCircles we'll need more info about the creation of newGray and circles.
here is an example i've found on the javaCV page (Link)
IplImage gray = cvCreateImage( cvSize( img.width, img.height ), IPL_DEPTH_8U, 1 );
cvCvtColor( img, gray, CV_RGB2GRAY );
// smooth it, otherwise a lot of false circles may be detected
cvSmooth(gray,gray,CV_GAUSSIAN,9,9,2,2);
CvMemStorage circles = CvMemStorage.create();
CvSeq seq = cvHoughCircles(gray, circles.getPointer(), CV_HOUGH_GRADIENT,
2, img.height/4, 100, 100, 0, 0);
for(int i=0; i<seq.total; i++){
float xyr[] = cvGetSeqElem(seq,i).getFloatArray(0, 3);
CvPoint center = new CvPoint(Math.round(xyr[0]), Math.round(xyr[1]));
int radius = Math.round(xyr[2]);
cvCircle(img, center.byValue(), 3, CvScalar.GREEN, -1, 8, 0);
cvCircle(img, center.byValue(), radius, CvScalar.BLUE, 3, 8, 0);
}
from what i've seen in the implementation of cvHoughCircles, the answer is saved in the circles buff and at the end they create from it the CvSeq to return, so if you've allocated the circles buff wrong, it wont work.
EDIT:
as you can see, the CvSeq instance in case of the return from cvHoughCircles is a list of point-values, that is probably why the assertion failed. you cannot convert this CvSeq into a cv::Mat.. because its just not a cv::Mat. to get only the circles returned from cvHoughCircles in an cv::Mat instance, you'll need to create a new cv::Mat instance and than draw onto it all the circles in the CvSeq - as seen in the provided example above.
than the warping will work (you'll have a cv::Mat instance, and that is what the function expect - a cv::Mat as the only element in the CvSeq)
END EDIT
here is the c++ reference for CvSeq
and if you want to fiddle with the source code than
cvarrToMat is in matrix.cpp
CV_ELEM_SIZE is in types_c.h
cvWarpPerspective is in imgwarp.cpp
cvHoughCircles is in hough.cpp
I hope that will help.
BTW, your next error will probably be:
cv::warpPerspective in the C++ OpencCv asserts that dst.data != src.data
thus
cvWarpPerspective(seq, seq, mmat);
wont work cause your source mat and destination mat referencing the same data.
Not all the functions in OpenCV (and image processing in general) work in-situ (because there is no in-situ algorithm or because its slower then the other version eg. transpose of an n*n mat will work in-situ, but n*m where n!=m will be harder to do in-situ and might be slower)
you cant assume the using the src matrix as the dst will work.