I got a little problem with the depth map to point color map,
i simply threshold the nearst depth (about 70-80cm), then i bitwise and the thresholded depth image to corresponding color map,
Mat depthFilter(Mat depth,Mat color){
Mat I;
depth.convertTo(I, CV_8UC1, 255.0 / 4096.0);
unsigned char *input = (unsigned char*)(I.data);
for (int i = 0; i < I.cols; i++){
for (int j = 0; j < I.rows; j++){
int pixel = input[I.cols*j + i];
if (!(pixel <52 && pixel >42)){
input[I.cols*j + i] = 0;
}
else
{
input[I.cols*j + i] = 255;
}
}
}
cvtColor(color, color, CV_BGR2GRAY);
bitwise_and(I, color, I);
return I;
}
(I'm using OpenCvKinect, which uses OpenNi and OpenCv)
But my problem is, the point's are not the same.. I think i need to find some relation between two images, but how :)!
http://postimg.org/image/hyxt25bwd/
I would see Why kinect color and depth won't align correctly? as they are having a similar problem in matlab. The answer suggest to use OpenNI's AlternateViewCapability class to align the images. This is the documentation from the older version of OpenNI (1.5) as I cannot find the 2.0 documentation for C++, but there is probably a similar method. The images on that answer show the difference the shift made.
The code is essentially
depth.GetAlternativeViewPointCap().SetViewPoint(image); //depth is depth generator
//image is color generator
I am not sure if you have already solved the problem of alignment, however this has been implemented within OpenCVKinect Wrappers that you are already using.
To acquire aligned Depth and Color images from Kinect, you need to use setMode function as follows:
setMode(C_MODE_DEPTH | C_MODE_COLOR | C_MODE_ALIGNED);
Related
I cannot see what I am doing wrong after checking the code a thousand times.
The algorithm is very simple: I have a CV_16U image with the disparity values called disp, and I am trying to implement the building of the u and v disparities in order to detect obstacles.
Mat v_disparity, u_disparity;
v_disparity=Mat::zeros(disp.rows,numberOfDisparities*16, CV_16U);
u_disparity=Mat::zeros(numberOfDisparities*16,disp.cols, CV_16U);
for(int i = 0; i < disp.rows; i++)
{
d = disp.ptr<ushort>(i); //d[j] is the disparity value
for (int j = 0; j < disp.cols; ++j)
{
v_disparity.at<uchar>(i,(d[j]))++;
u_disparity.at<uchar>((d[j]),j)++;
}
}
The problem is that when I use imshow to print both disparities after converting to 8bit Unsigned. The u-disparity is wrong, since it has the shape it should, but it's half the horizontal dimension, being the right pixels black.
I finally figured it out. It was just that I used a wrong template while accessing to the value of the pixels in u and v-disparities. In the v-disparity I didn't detect it since I thought there was no pixels in disp with high disparity values.
To sum up, the following lines:
v_disparity.at<uchar>(i,(d[j]))++;
u_disparity.at<uchar>((d[j]),j)++;
must be replaced by:
v_disparity.at<ushort>(i,(d[j]))++;
u_disparity.at<ushort>((d[j]),j)++;
since both images are CV_16U, and the type uchar is 8 bit, not 16 bit.
I'm trying to to add noise to an Image & then Denoise it to test my DeNoising algorithm! So for benchmark i'm referring this Online Test samples. I'm trying to replicate the Noise model.
With reference to this threads 1 , 2 I'm adding noise to image like this!
Mat mSource_Bgr;
mSource_Bgr= imread(FileName_S,1);
double m_NoiseStdDev=10;
Mat mNoise_Bgr = mSource_Bgr.clone();
Mat mGaussian_noise = Mat(mSource_Bgr.size(),CV_8UC3);
randn(mGaussian_noise,0,m_NoiseStdDev);
mNoise_Bgr += mGaussian_noise;
normalize(mNoise_Bgr,mNoise_Bgr,0, 255, CV_MINMAX, CV_8UC3);
imshow("Output Window",mNoise_Bgr);
//imshow("Gaussian Noise",mGaussian_noise);
My Input Image
Output Image with Noise
Problem:
Adding Noise to the image alters overall brightness of the Image which in turn alters my final results PSNR!
I want to get the results as much as closer to this one!
What i have tried so far!
I have tried to add the noise only in the color channel.
Convert the Input image into YUV Color space
Add the Noise only in the UV Color Channels & Keep the Y channel unaltered.
Results are very bad & the overall color of the image is getting altered! Will add the code if needed!
So any advice regarding this is much appreciated! May be give me some formulas for adding Noise to the image!
Thank you #Andrey Smorodov For your insights!
I got it working! Here is my updated code for adding Noise in a Color Image. Hope this will be useful for someone!
#include "opencv2/imgproc/imgproc.hpp"
#include "opencv2/highgui/highgui.hpp"
#include <iostream>
using namespace cv;
using namespace std;
inline BYTE Clamp(int n)
{
n = n>255 ? 255 : n;
return n<0 ? 0 : n;
}
bool AddGaussianNoise(const Mat mSrc, Mat &mDst,double Mean=0.0, double StdDev=10.0)
{
if(mSrc.empty())
{
cout<<"[Error]! Input Image Empty!";
return 0;
}
Mat mGaussian_noise = Mat(mSrc.size(),CV_16SC3);
randn(mGaussian_noise,Scalar::all(Mean),Scalar::all(StdDev));
for (int Rows = 0; Rows < mSrc.rows; Rows++)
{
for (int Cols = 0; Cols < mSrc.cols; Cols++)
{
Vec3b Source_Pixel= mSrc.at<Vec3b>(Rows,Cols);
Vec3b &Des_Pixel= mDst.at<Vec3b>(Rows,Cols);
Vec3s Noise_Pixel= mGaussian_noise.at<Vec3s>(Rows,Cols);
for (int i = 0; i < 3; i++)
{
int Dest_Pixel= Source_Pixel.val[i] + Noise_Pixel.val[i];
Des_Pixel.val[i]= Clamp(Dest_Pixel);
}
}
}
return true;
}
bool AddGaussianNoise_Opencv(const Mat mSrc, Mat &mDst,double Mean=0.0, double StdDev=10.0)
{
if(mSrc.empty())
{
cout<<"[Error]! Input Image Empty!";
return 0;
}
Mat mSrc_16SC;
Mat mGaussian_noise = Mat(mSrc.size(),CV_16SC3);
randn(mGaussian_noise,Scalar::all(Mean), Scalar::all(StdDev));
mSrc.convertTo(mSrc_16SC,CV_16SC3);
addWeighted(mSrc_16SC, 1.0, mGaussian_noise, 1.0, 0.0, mSrc_16SC);
mSrc_16SC.convertTo(mDst,mSrc.type());
return true;
}
int main(int argc, const char* argv[])
{
Mat mSource= imread("input.png",1);
imshow("Source Image",mSource);
Mat mColorNoise(mSource.size(),mSource.type());
AddGaussianNoise(mSource,mColorNoise,0,10.0);
imshow("Source + Color Noise",mColorNoise);
AddGaussianNoise_Opencv(mSource,mColorNoise,0,10.0);//I recommend to use this way!
imshow("Source + Color Noise OpenCV",mColorNoise);
waitKey();
return 0;
}
Looks like your noise matrix can't get negative values as it have unsigned char element type. Try operate with real valued matrices, it should help.
There are mainly two methods to add say awgn noise (mean = 0, standard deviation = 30) to a colored image.
First: You can add the awgn noise of mean = 0, standard deviation = 30 to each of Red, Green, and Blue channels independently (or any other color model-HSI, YUV, Lab); and then combine the noisy channels to form the colored noisy image.
Second: To use the in-built function to add noise to the colored image directly. eg. imnoise() in Matlab.
I tried with both the methods (imnoise and independently), I got the same result.
You mentioned "I have tried to add the noise only in the color channel.
Convert the Input image into YUV Color space
Add the Noise only in the UV Color Channels & Keep the Y channel unaltered."
If you are using the YUV color model, I would suggest you do the opposite. Keep U, and V channel unaltered and add noise only to the Y channel only.
I have the histogram for an image which i have calculated. I want to display this as an image so that I can actually see the histogram. I think my problem is to do with scaling although i am slightly confused over the co ordinate system starting with 0,0 in the top left as well.
int rows = channel.rows;
int cols = channel.cols;
int hist[256] = {0};
for(int i = 0; i<rows; i++)
{
for(int k = 0; k<cols; k++ )
{
int value = channel.at<cv::Vec3b>(i,k)[0];
hist[value] = hist[value] + 1;
}
}
Mat histPlot = cvCreateMat(256, 500,CV_8UC1);
for(int i = 0; i < 256; i++)
{
int mag = hist[i];
line(histPlot,Point(i,0),Point(i,mag),Scalar(255,0,0));
}
namedWindow("Hist",1);
imshow("Hist",histPlot);
This is my calculation for creating my histogram and displaying the result. If i do mag/100 in my second loop then i get some resemblance of a plot appearing (although upside down). I call this method whenever i adjust a value of my image, so the histogram should also change shape, which it doesn't appear to do. Any help in scaling the histogram and displaying it properly is appreciated.
please don't use cvCreateMat ( aka, the old c-api ), you also seem to have rows and cols wrong, additionally, if you want a color drawing, you need a color image as well, so make that:
Mat histPlot( 500, 256, CV_8UC3 );
image origin is top-left(0,0), so you've got to put y in reverse:
line(histPlot,Point(i,histPlot.rows-1),Point(i,histPlot.rows-1-mag/100),Scalar(255,0,0));
I wrote a digital OCR for ios.
I have a test image png with two digits 5 and 4.
I find the contours. How do I transfer the contour one at tesseract?
init tesseract:
tess = new tesseract::TessBaseAPI();
tess->Init([dataPath cStringUsingEncoding:NSUTF8StringEncoding], "eng");
tess->SetPageSegMode(tesseract::PSM_SINGLE_CHAR); //<-- !!!!
tess->tesseract::TessBaseAPI::SetVariable("tessedit_char_whitelist", "0123456789");
Function for detect contours:
- (std::vector<std::vector<cv::Point> >)findSquaresInImage:(cv::Mat)_image {
std::vector<std::vector<cv::Point> > squares;
cv::Mat pyr, timg, gray0(_image.size(), CV_8U), gray;
int thresh = 50, N = 11;
cv::pyrDown(_image, pyr, cv::Size(_image.cols/2, _image.rows/2));
cv::pyrUp(pyr, timg, _image.size());
std::vector<std::vector<cv::Point> > contours;
int ch[] = {0, 0};
mixChannels(&timg, 1, &gray0, 1, ch, 1);
for( int l = 0; l < N; l++ ) {
if( l == 0 ) {
cv::Canny(gray0, gray, 0, thresh, 5);
cv::dilate(gray, gray, cv::Mat(), cv::Point(-1,-1));
}
else {
gray = gray0 >= (l+1)*255/N;
}
cv::findContours(gray, contours, CV_RETR_EXTERNAL, CV_CHAIN_APPROX_SIMPLE);
std::vector<cv::Point> approx;
CvRect rec1;
std::string str;
std::map<int,IplImage*> pic_list;
for( size_t i = 0; i < contours.size(); i++ )
{
rec1 = cv::boundingRect(contours[i]);
if (rec1.height > 0.5*gray.rows && rec1.width < 0.756*gray.cols) {
NSLog(#"%d %d %d %d", rec1.width, rec1.height, rec1.x, rec1.y);
cv::approxPolyDP(cv::Mat(contours[i]), approx, arcLength(cv::Mat(contours[i]), true)*0.02, true);
squares.push_back(approx);
}
}
}
return squares; }
function for draw contours:
cv::Mat debugSquares( std::vector<std::vector<cv::Point> > squares, cv::Mat image ) {
for ( int i = 0; i< squares.size(); i++ ) {
// draw contour
cv::drawContours(image, squares, i, cv::Scalar(255,0,0), 1, 8, std::vector<cv::Vec4i>(), 0, cv::Point());
// draw bounding rect
cv::Rect rect = boundingRect(cv::Mat(squares[i]));
cv::rectangle(image, rect.tl(), rect.br(), cv::Scalar(0,255,0), 2, 8, 0);
// draw rotated rect
cv::RotatedRect minRect = minAreaRect(cv::Mat(squares[i]));
cv::Point2f rect_points[4];
minRect.points( rect_points );
for ( int j = 0; j < 4; j++ ) {
cv::line( image, rect_points[j], rect_points[(j+1)%4], cv::Scalar(0,0,255), 1, 8 ); // blue
}
}
return image;
}
method for btn Click:
- (IBAction)onMath:(id)sender {
UIImage *image = [UIImage imageNamed:#"test1.png"];
cv::Mat iMat = [self cvMatFromUIImage:image];
std::vector<std::vector<cv::Point> > sq = [self findSquaresInImage:iMat];
cv::Mat hui = debugSquares(sq, iMat);
image = [self UIImageFromCVMat:hui];
self.imView.image = image;
}
image after:
link to project on github: https://github.com/MaxPatsy/iORC
Can you check this answer here
I described some tips for preparing images for Tesseract here: Using tesseract to recognize license plates
In your example, there are several things going on...
You need to get the text to be black and the rest of the image white (not the reverse). That's what character recognition is tuned on. Grayscale is ok, as long as the background is mostly full white and the text mostly full black; the edges of the text may be gray (antialiased) and that may help recognition (but not necessarily - you'll have to experiment)
One of the issues you're seeing is that in some parts of the image, the text is really "thin" (and gaps in the letters show up after thresholding), while in other parts it is really "thick" (and letters start merging). Tesseract won't like that :) It happens because the input image is not evenly lit, so a single threshold doesn't work everywhere. The solution is to do "locally adaptive thresholding" where a different threshold is calculated for each neighbordhood of the image. There are many ways of doing that, but check out for example:
Adaptive gaussian thresholding in OpenCV with cv2.adaptiveThreshold(...,cv2.ADAPTIVE_THRESH_GAUSSIAN_C,...)
Local Otsu's method
Local adaptive histogram equalization
Another problem you have is that the lines aren't straight. In my experience Tesseract can handle a very limited degree of non-straight lines (a few percent of perspective distortion, tilt or skew), but it doesn't really work with wavy lines. If you can, make sure that the source images have straight lines :) Unfortunately, there is no simple off-the-shelf answer for this; you'd have to look into the research literature and implement one of the state of the art algorithms yourself (and open-source it if possible - there is a real need for an open source solution to this). A Google Scholar search for "curved line OCR extraction" will get you started, for example:
Text line Segmentation of Curved Document Images
Lastly: I think you would do much better to work with the python ecosystem (ndimage, skimage) than with OpenCV in C++. OpenCV python wrappers are ok for simple stuff, but for what you're trying to do they won't do the job, you will need to grab many pieces that aren't in OpenCV (of course you can mix and match). Implementing something like curved line detection in C++ will take an order of magnitude longer than in python (* this is true even if you don't know python).
Good luck!
I'm using Emgu.CV to perform some basic image manipulation and composition. My images are loaded as Image<Bgra,Byte>.
Question #1: When I use the Image<,>.Add() method, the images are always blended together, regardless of the alpha value. Instead I'd like them to be composited one atop the other, and use the included alpha channel to determine how the images should be blended. So if I call image1.Add(image2) any fully opaque pixels in image2 would completely cover the pixels from image1, while semi-transparent pixels would be blended based on the alpha value.
Here's what I'm trying to do in visual form. There's a city image with some "transparent holes" cut out, and a frog behind. This is what it should look like:
And this is what openCV produces.
How can I get this effect with OpenCV? And will it be as fast as calling Add()?
Question #2: is there a way to perform this composition in-place instead of creating a new image with each call to Add()? (e.g. image1.AddImageInPlace(image2) modifies the bytes of image1?)
NOTE: Looking for answers within Emgu.CV, which I'm using because of how well it handles perspective warping.
Before OpenCV 2.4 there was no support of PNGs with alpha channel.
To verify if your current version supports it, print the number of channels after loading an image that you are certain to be RGBA. If it supports, the application will output the number 4, else it will output number 3 (RGB). Using the C API you would do:
IplImage* t_img = cvLoadImage(argv[1], CV_LOAD_IMAGE_UNCHANGED);
if (!t_img)
{
printf("!!! Unable to load transparent image.\n");
return -1;
}
printf("Channels: %d\n", t_img->nChannels);
If you can't update OpenCV:
There are some posts around that try to bypass this limitation but I haven't tested them myself;
The easiest solution would be to use another API to load the image and blend it, check blImageBlending;
Another alternative, not as lightweight, is to use Qt.
If your version already supports PNGs with RGBA:
Take a look at Emulating photoshop’s blending modes in OpenCV. It implements several Photoshop blending modes and I imagine you are capable of converting that code to .Net.
EDIT:
I had to deal with this problem recently and I've demonstrated how to deal with it on this answer.
You'll have to iterate through each pixel. I'm assuming image 1 is the frog image, and image 2 is the city image, with image1 always being bigger than image2.
//to simulate image1.AddInPlace(image2)
int image2w = image2.Width;
int image2h = image2.Height;
int i,j;
var alpha;
for (i = 0; i < w; i++)
{
for (j = 0; j < h; j++)
{
//alpha=255 is opaque > image2 should be used
alpha = image2[3][j,i].Intensity;
image1[j, i]
= new Bgra(
image2[j, i].Blue * alpha + (image1[j, i].Blue * (255-alpha)),
image2[j, i].Green * alpha + (image1[j, i].Green * (255-alpha)),
image2[j, i].Red * alpha + (image1[j, i].Red * (255-alpha)));
}
}
Using Osiris's suggestion as a starting point, and having checked out alpha compositing on Wikipedia, i ended up with the following which worked really nicely for my purposes.
This was used this with Emgucv. I was hoping that the opencv gpu::AlphaComposite methods were available in Emgucv which I believe would have done the following for me, but alas the version I am using didn't appear to have them implemented.
static public Image<Bgra, Byte> Overlay( Image<Bgra, Byte> image1, Image<Bgra, Byte> image2 )
{
Image<Bgra, Byte> result = image1.Copy();
Image<Bgra, Byte> src = image2;
Image<Bgra, Byte> dst = image1;
int rows = result.Rows;
int cols = result.Cols;
for (int y = 0; y < rows; ++y)
{
for (int x = 0; x < cols; ++x)
{
// http://en.wikipedia.org/wiki/Alpha_compositing
double srcA = 1.0/255 * src.Data[y, x, 3];
double dstA = 1.0/255 * dst.Data[y, x, 3];
double outA = (srcA + (dstA - dstA * srcA));
result.Data[y, x, 0] = (Byte)(((src.Data[y, x, 0] * srcA) + (dst.Data[y, x, 0] * (1 - srcA))) / outA); // Blue
result.Data[y, x, 1] = (Byte)(((src.Data[y, x, 1] * srcA) + (dst.Data[y, x, 1] * (1 - srcA))) / outA); // Green
result.Data[y, x, 2] = (Byte)(((src.Data[y, x, 2] * srcA) + (dst.Data[y, x, 2] * (1 - srcA))) / outA); // Red
result.Data[y, x, 3] = (Byte)(outA*255);
}
}
return result;
}
A newer version, using emgucv methods. rather than a loop. Not sure it improves on performance.
double unit = 1.0 / 255.0;
Image[] dstS = dst.Split();
Image[] srcS = src.Split();
Image[] rs = result.Split();
Image<Gray, double> srcA = srcS[3] * unit;
Image<Gray, double> dstA = dstS[3] * unit;
Image<Gray, double> outA = srcA.Add(dstA.Sub(dstA.Mul(srcA)));// (srcA + (dstA - dstA * srcA));
// Red.
rs[0] = srcS[0].Mul(srcA).Add(dstS[0].Mul(1 - srcA)).Mul(outA.Pow(-1.0)); // Mul.Pow is divide.
rs[1] = srcS[1].Mul(srcA).Add(dstS[1].Mul(1 - srcA)).Mul(outA.Pow(-1.0));
rs[2] = srcS[2].Mul(srcA).Add(dstS[2].Mul(1 - srcA)).Mul(outA.Pow(-1.0));
rs[3] = outA.Mul(255);
// Merge image back together.
CvInvoke.cvMerge(rs[0], rs[1], rs[2], rs[3], result);
return result.Convert<Bgra, Byte>();
I found an interesting blog post on internet, which I think is related to what you are trying to do.
Please have a look at the Creating Overlays Method (archive.org link). You can use this idea to implement your own function to add two images in the way you mentioned above, making some particular areas in the image transparent while leaving the rest as it is.