I want to read a png image using the libpng and store the pixel values into a std::vectorstd::vector<uint8_t>.
But the compilator throw an error.
My C++ code is :
char fileName[] = "test.png";
// We try to open the image file
FILE * inputImageFile;
if((inputImageFile = fopen(fileName, "rb")) == NULL) {
throw std::runtime_error("Error : can't open this file");
}
// We start the decompression
png_structp png = png_create_read_struct(PNG_LIBPNG_VER_STRING, NULL, NULL, NULL);
png_infop imageInfo = png_create_info_struct(png);
png_init_io(png, inputImageFile);
png_read_info(png, imageInfo);
// We store the image informations into privates variables
unsigned int width = png_get_image_width(png, imageInfo);
unsigned int height = png_get_image_height(png, imageInfo);
unsigned int colorType = png_get_color_type(png, imageInfo);
unsigned int bitDepth = png_get_bit_depth(png, imageInfo);
// We continue to read the image
png_read_update_info(png, imageInfo);
// We create a table to store the pixels values
png_bytep * rowPointers;
rowPointers = (png_bytep*)malloc(sizeof(png_bytep) * height);
// We allocate memory
for(unsigned int i = 0; i < height; i++) {
rowPointers[i] = (png_byte*)malloc(png_get_rowbytes(png, imageInfo));
}
// We finish the decompression
png_read_image(png, rowPointers);
png_destroy_read_struct(&png, &imageInfo, NULL);
std::cout << "Image Dimensions : " << width << "x" << height <<"\n";
// Now you can get the rgb values like this :
int x = 4;
int y = 7;
png_bytep pixel = &(rowPointers[y][x * 4]); // 4 for R, G, B, and the alpha value (the transparance)
// The "+" is here to print the value as a number
std::cout << "Image Pixel (x = 4, y = 7) : RGB(" << +pixel[0] << ", " << +pixel[1] << ", " << +pixel[2] << ")" << "\n";
std::cout << "Image Pixel (x = 4, y = 7) : transparance : " << +pixel[3] << "\n";
I have compiled my code like this : (on Linux)
g++ -o yourBinary youFile.cc -lpng
Now I want to replace this :
// We create a table to store the pixels values
png_bytep * rowPointers;
rowPointers = (png_bytep*)malloc(sizeof(png_bytep) * height);
// We allocate memory
for(unsigned int i = 0; i < height; i++) {
rowPointers[i] = (png_byte*)malloc(png_get_rowbytes(png, imageInfo));
}
// We finish the decompression
png_read_image(png, rowPointers);
png_destroy_read_struct(&png, &imageInfo, NULL);
// Now you can get the rgb values like this :
int x = 4;
int y = 7;
png_bytep pixel = &(rowPointers[y][x * 4]); // 4 for R, G, B, and the alpha value (the transparance)
std::cout << "Image Dimensions : " << width << "x" << height <<"\n";
std::cout << "Image Pixel (x = 4, y = 7) : RGB(" << +pixel[0] << ", " << +pixel[1] << ", " << +pixel[2] << ")" << "\n";
std::cout << "Image Pixel (x = 4, y = 7) : transparance : " << +pixel[3] << "\n";
By this :
std::vector<std::vector<uint8_t>> pixels;
pixels.reserve(height);
// We finish the decompression
png_read_image(png, pixels);
png_destroy_read_struct(&png, &imageInfo, NULL);
// Now you can get the rgb values like this :
int x = 4;
int y = 7;
std::cout << "Image Dimensions : " << width << "x" << height <<"\n";
std::cout << "Image Pixel (x = 4, y = 7) : RGB(" << +pixels[y][x * 4] << ", " << +pixels[y][x * 4 + 1] << ", " << +pixels[y][x * 4 + 2] << ")" << "\n";
std::cout << "Image Pixel (x = 4, y = 7) : transparance : " << +pixels[y][x * 4 + 3] << "\n";
The error is :
test.cc: In function ‘int main()’:
test.cc:60:29: error: cannot convert ‘std::vector<std::vector<unsigned char> >’ to ‘png_bytepp {aka unsigned char**}’ for argument ‘2’ to ‘void png_read_image(png_structrp, png_bytepp)’
png_read_image(png, pixels);
But this doesn't work.
Can someone help me ?
You need to do more to pixels to get something compatible with png_read_image, and you need to fill pixels before using it.
#include <algorithm>
size_t row_bytes = png_get_rowbytes(png, imageInfo);
std::vector<std::vector<png_byte>> pixels (height, std::vector<png_byte>(row_bytes));
std::vector<png_byte *> ppixels(height);
std::transform(pixels.begin(), pixels.end(), ppixels.begin(), [](auto & vec){ return vec.data(); });
png_read_image(png, ppixels.data());
I have encountered on designing program to allow capturing images every second from video files (avi, mp4, etc...).
First, I was able to capture images frame by frame from video file.
Second, I was able to analyze pixel color values from images in the same folder at the same time and saved pixel value in the txt file.
And here I have some problem. I am now trying to combine these two codes at once, but I have strange results. I refer the code below.
int main(){
VideoCapture cap("D:\\data\\extra\\video200ul.avi");
if (!cap.isOpened())
return -1;
Ptr<BackgroundSubtractor> pMOG2 = createBackgroundSubtractorMOG2(20, 16, true);
Mat fg_mask;
Mat frame;
int count = 0;
String name, folder;
for (;;) {
// Get frame
cap >> frame; // get a new frame from video
++count;
// Update counter
// Background subtraction
if (count % 2 == 0) {
pMOG2->apply(frame, fg_mask, 0.001);
cout << count << endl;
if (!frame.empty()) {
imshow("frame", frame);
// imshow("fg_mask", fg_mask);
}
// Save foreground mask
name = "mask" + std::to_string(count) + ".png";
// string name = "mask_" + std::to_string(static_cast<long long>(count) + ".png";
folder = imwrite("D:\\data\\extra\\" + name, frame);
}
anal(folder);
}
waitKey(0);
return 0;
}
First, The code above I wrote is for capturing images frame by frame from video file. However, if I got the images per frame, I will have so many pictures on my folder, so I would like to capture an image per second from the video file. I have tried to use CV_CAP_PROP_POS_MSEC instead using cap << frame, but it did not work for me.
Second, when I merge this code to another code what I wrote below, it showed some error messages like, "libpng warning image width, length, data are zero in ihdr."
int anal(String folder) {
folder = "D:\\data\\extra\\*.png";
vector<String> filenames;
glob(folder, filenames);
cv::Mat ori_image;
for (size_t i = 0; i < filenames.size(); ++i) {
ori_image = imread(filenames[i], IMREAD_COLOR);
if (ori_image.empty()) {
cout << "Check your file again." << std::endl;
return -1;
}
rectangle(ori_image, Point(215, 98), Point(245, 110), Scalar(0, 255, 255), 1);
imshow("Original Image", ori_image);
cv::Scalar sums;
sums = cv::sum(ori_image);
double totalSum = sums[0] + sums[1] + sums[2];
if (totalSum <= 0) {
cout << "$$ RGB percentage $$" << " \n\n";
cout << "R: " << 100.0 / 3 << " % \n";
cout << "G: " << 100.0 / 3 << " % \n";
cout << "B: " << 100.0 / 3 << " % \n\n";
}
else {
cout << "$$ RGB percentage $$" << " \n\n"; // red value
cout << "R: " << sums[2] / totalSum * 100 << " % \n"; // red value
cout << "G: " << sums[1] / totalSum * 100 << " % \n"; // green value
cout << "B: " << sums[0] / totalSum * 100 << " % \n\n"; // blue value
}
}
as I prepared the code above, I tried to calculate red, blue, green percentages of all the captured images from the video. However, when I separate these two code and run them, they worked fine, but if I merge them together, It showed error messages.
I would like to combine these two code for analysis for color values from the captured images at video every second.
Please help me out this problem.
Thank you in advance.
-----------Edited part----------------------
I used your revised version and applied to my updated code,
void imageAnalysis(std::string folder, cv::Mat frame){
cv::Mat ori_image = frame.clone();
std::string path = folder;
cv::rectangle(ori_image, Point(215, 105), Point(245, 120), Scalar(0, 255, 255), 1);
cv::imshow("Original Image", ori_image);
cv::waitKey(1);
String folder = "D:\\data\\dfdf\\*.png";
vector<String> filenames;
cv::glob(path, filenames);
for (size_t t = 0; t < filenames.size(); t++) {
ori_image = imread(filenames[t], IMREAD_COLOR); // ori_image
if (ori_image.empty()) { //ori_image
cout << "Check your file again." << "\n";
break;
//return -1;
}
rectangle(ori_image, Point(215, 105), Point(245, 120), Scalar(0, 255, 255), 1);
imshow("Original Image", ori_image);
cv::waitKey(1);
Mat image_HSV;
cvtColor(ori_image, image_HSV, CV_BGR2HSV);
double h = 0.0;
double s = 0.0;
double v = 0.0;
int col = image_HSV.cols; // 480
int row = image_HSV.rows; // 272
int corow = ((col - 235) - 215) * ((row - 152) - 108);
Mat mask;
inRange(image_HSV, Scalar(100, 0, 0), Scalar(100, 255, 255), mask); // convert binary
image_HSV.setTo(Scalar(0, 0, 0), mask);
for (int i = 108; i < row - 152; i++) {
for (int j = 215; j < col - 235; j++) {
Vec3b hsv = image_HSV.at<cv::Vec3b>(i, j);
h += (int)(hsv.val[0]);
s += (int)(hsv.val[1]);
v += (int)(hsv.val[2]);
if (hsv[0] != 100) {
hsv[0] = 0;
hsv[1] = 0;
hsv[2] = 0;
}
}
}
cout << "$$ Hue(H), Saturation(S), Brightness(V) $$" << filenames[t] << " !! \n\n";
cout << "H: " << h / corow * 360 / 180 << " % \n"; //
cout << "S: " << s / corow * 100 / 255 << " % \n";
cout << "V: " << v / corow * 100 / 255 << " % \n\n";
std::ofstream file("D:\\data\\dfdf\\result_4.txt", std::ios_base::app);
file << v / corow * 100 / 255 << " \n"; // v value
file.close();
}
}
As you can see the imageAnalysis() function, I added std::string folder for the path of extracted images from video clip. However, when I applied this code, I have really weird results like below..
enter image description here
I thought I am supposed to get color value from every 24th image but as you see the results above, I got color values from all images in random order.
Thank you in advance.
It was really nice to learn how to code in efficient way!!
Just to clear the error you mentioned about CV_CAP_PROP_POS_MSEC in your comments:
when I apply CV_CAP_PROP_POS_MSEC to my code, I found some error
messages like "CV_CAP_PROP_POS_MSEC is not defined."
A lot of the constant values are scoped in OpenCV. That means, CV_CAP_PROP_POS_MSEC is not defined, but cv::CV_CAP_PROP_POS_MSEC is. You can also obtain the FPS with cv::CAP_PROP_FPS.
Now to your code, I would actually do something that does not require to save and load the image, but rather pass the images to be processed, like this:
#include "opencv2/opencv.hpp"
#include <iostream>
int main(){
cv::VideoCapture cap("D:\\data\\extra\\video200ul.avi");
if (!cap.isOpened())
{
std::cout << "Could not open video" << std::endl;
return -1;
}
cv::Ptr<cv::BackgroundSubtractor> pMOG2 = cv::createBackgroundSubtractorMOG2(20, 16, true);
cv::Mat fg_mask, frame;
int count = 0;
const int fps = 24; // you may set here the fps or get them from the video
std::string name, folder;
// with cap.read you can check already if the video ended
while (cap.read(frame)) {
// Background subtraction
if (count % fps == 0) {
pMOG2->apply(frame, fg_mask, 0.001);
// Save foreground mask
name = "mask" + std::to_string(count) + ".png";
bool result = cv::imwrite("D:\\data\\extra\\" + name, frame);
imageAnalysis(frame, count);
}
// at the end of the loop so that the first image is used
++count;
}
cv::waitKey(0);
return 0;
}
And the imageAnalysis function is defined as:
// You can pass cv::Mat as value, it is almost like a smart pointer
void imageAnalysis(cv::Mat frame, int count)
{
cv::Mat ori_image = frame.clone();
cv::rectangle(ori_image, Point(215, 98), Point(245, 110), Scalar(0, 255, 255), 1);
// each imshow needs a waitKey to update the window in which it is being shown
cv::imshow("Original Image", ori_image);
cv::waitKey(1);
cv::Scalar sums;
sums = cv::sum(ori_image);
double totalSum = sums[0] + sums[1] + sums[2];
std::ofstream output("D:\\data\\extra\\mask" + std::to_string(count) + ".txt");
if (totalSum <= 0)
{
std::cout << "$$ RGB percentage $$" << std::endl << std::endl;
std::cout << "R: " << 100.0 / 3 << std::endl;
std::cout << "G: " << 100.0 / 3 << std::endl;
std::cout << "B: " << 100.0 / 3 << std::endl << std::endl;
output << "$$ RGB percentage $$" << std::endl << std::endl;
output << "R: " << 100.0 / 3 << std::endl;
output << "G: " << 100.0 / 3 << std::endl;
output << "B: " << 100.0 / 3 << std::endl << std::endl;
}
else {
std::cout << "$$ RGB percentage $$" << std::endl << std::endl;
std::cout << "R: " << sums[2] / totalSum * 100 << std::endl; // red value
std::cout << "G: " << sums[1] / totalSum * 100 << std::endl; // green value
std::cout << "B: " << sums[0] / totalSum * 100 << std::endl << std::endl; // blue value
output << "$$ RGB percentage $$" << std::endl << std::endl;
output << "R: " << sums[2] / totalSum * 100 << std::endl; // red value
output << "G: " << sums[1] / totalSum * 100 << std::endl; // green value
output << "B: " << sums[0] / totalSum * 100 << std::endl << std::endl; // blue value
}
}
Some comments of the code above, I replaced the cap >> frame to cap.read(frame). It is the same functionality, but the later gives a bool result that is false if it could not grab the image, like if the video is over. I change the count add at the end, yo you get the frames 0,23,... this way the first one will be use as well. Finally, you should use the namespaces cv::, std:: etc. This is just best practice, it avoids ambiguities and problems that may arise with certain libraries.
If you do not need the image in disk, but only the analysis, then remove the saving part and pass every frame to the imageAnalysis function, this way you may have more data for your statistics. Also, consider returning the cv:Scalar of sums in the function and then you can do some statistics of the whole second or the whole video.
If you have any question, feel free to ask in the comments.
I am doing some image processing using ITK and then using VTK to print the results in a .png format however, the output image is always black.
Currently, I am converting itk::Image to vtk::vtkImageData using the itk::ImagetoVTKImageFilter(typedeffed to ITKtoVTKFilterType in my code).
ITKtoVTKFilterType::Pointer itk2vtkGray = ITKtoVTKFilterType::New();
itk2vtkGray->SetInput(grayBinary); //grayBinary is of type itk::Image<unsigned short, 2>
itk2vtkGray->Update();
vtkSmartPointer<vtkImageData> grayVTK = vtkSmartPointer<vtkImageData>::New();
grayVTK->SetExtent(extent);
grayVTK->SetSpacing(m_spacing);
grayVTK->SetScalarTypeToUnsignedShort();
grayVTK->SetNumberOfScalarComponents(1);
grayVTK->AllocateScalars();
grayVTK->DeepCopy(static_cast<vtkImageData*>(itk2vtkGray->GetOutput()));
//grayVTK = itk2vtkGray->GetOutput();
I have even confirmed that my VTK ImageData contains values of either 255 or 0 using the following code.
int *dims = grayVTK->GetDimensions();
std::cout << "Dims: " << " x: " << dims[0] << " y: " << dims[1] << " z: " << dims[2] << std::endl;
std::cout << "Number of points: " << grayVTK->GetNumberOfPoints() << std::endl;
std::cout << "Number of cells: " << grayVTK->GetNumberOfCells() << std::endl;
for (int y = 0; y < dims[1]; y++)
{
for (int x = 0; x < dims[0]; x++)
{
unsigned short *pixel = static_cast<unsigned short*>(grayVTK->GetScalarPointer(x,y,0));
std::cout << "PIXEL LOC/VAL "<< y*dims[0] + x << " " << pixel[0] <<std::endl;
}
std::cout << std::endl;
}
I then go on to do an ImageCast to ensure the type of the data is unsignedShort.
vtkSmartPointer<vtkImageCast> cast2 = vtkSmartPointer<vtkImageCast>::New();
cast2->SetInput(grayVTK);
cast2->SetOutputScalarTypeToUnsignedShort();
cast2->ClampOverflowOn();
cast2->Update();
Then finally I use vtkPNGwriter to output the .png files. Notice that I have tried to output both the actual vtkImageData as well as output from the ImageCastFilter.
vtkSmartPointer<vtkPNGWriter> writer =
vtkSmartPointer<vtkPNGWriter>::New();
writer->SetFileName(filename.toStdString().c_str());
writer->SetInputConnection(cast2->GetOutputPort());
//writer->SetInput(grayVTK); I have tried to method as well but to no success
writer->Write();
However, the .png output is always black. Does anyone know what I am doing wrong.
For future reference it seems that many PNG readers do not display 16 bit data. Hence the casting I was doing to unsigned short at the end should have rather been to char.
vtkSmartPointer<vtkImageCast> cast2 = vtkSmartPointer<vtkImageCast>::New();
cast2->SetInput(grayVTK);
cast2->SetOutputScalarTypeToChar();
cast2->ClampOverflowOn();
cast2->Update();
I am trying to make a terrain using a height map image in OpenGL. As a experiment i use 4x4 pixel image. this is a zoomed screen shot. so you can see the pixels.
This is a part of my code.
ILubyte * image = ilGetData();
int bpp = ilGetInteger(IL_IMAGE_BPP);
std::cout << "BPP = " << bpp << std::endl;
for (int z=0; z < terrainHeight; ++z)
{
for (int x=0; x < terrainWidth; ++x)
{
pVertices[z*terrainWidth+x] = NxVec3(NxF32(x),
NxF32(image[z*terrainWidth+x]*bpp), NxF32(z));
}
}
for (int i=0; i < vertexCount; ++i)
{
std::cout << "x = " << pVertices[i].x << "\t y = "
<< pVertices[i].y << "\t z = " << pVertices[i].z << std::endl;
}
Then, i'm getting the following result.
I'm expecting the zero values(for y-coordinate) for (0,0), (1,1), (2,2) and (3,3). but the result is different. why i'm not getting the expected results ?
I think it should be image[(z*terrainWidth+x)*bpp] instead of image[z*terrainWidth+x]*bpp.
I've already asked this question, but that was about FreeImage. Now I'm trying to do the same thing with ImageMagick (to be more correct, with Magick++).
All I need is to get the RGB value of pixels in an image with the ability to print it out onto the screen. I asked this in the ImageMagick forum, but it seems there is nobody there. :-( Can anybody help, please?
Version 6 API
Given an "Image" object, you have to request a "pixel cache", then work with it. Documentation is here and here:
// load an image
Magick::Image image("test.jpg");
int w = image.columns();
int h = image.rows();
// get a "pixel cache" for the entire image
Magick::PixelPacket *pixels = image.getPixels(0, 0, w, h);
// now you can access single pixels like a vector
int row = 0;
int column = 0;
Magick::Color color = pixels[w * row + column];
// if you make changes, don't forget to save them to the underlying image
pixels[0] = Magick::Color(255, 0, 0);
image.syncPixels();
// ...and maybe write the image to file.
image.write("test_modified.jpg");
Version 7 API
Access to pixels has changed in version 7 (see: porting), but low-level access is still present:
MagickCore::Quantum *pixels = image.getPixels(0, 0, w, h);
int row = 0;
int column = 0;
unsigned offset = image.channels() * (w * row + column);
pixels[offset + 0] = 255; // red
pixels[offset + 1] = 0; // green
pixels[offset + 2] = 0; // blue
#Sga's answer didn't work for me, I'm using the ImageMagick-7.0.7-Q8 (8 bit depth) library.
Here's how I did it, to scan an image pixel by pixel and output each one's RGB value:
// "InitializeMagick" called beforehand!
void processImage()
{
std::ifstream fin;
std::stringstream fs;
fs << "/img.png";
std::cout << "Opening image \"" << fs.str() << "\".." << std::endl;
try
{
Image img;
img.read( fs.str() );
int imgWidth = img.columns();
int imgHeight = img.rows();
std::cout << "Image width: " << imgWidth << std::endl;
std::cout << "Image height: " << imgHeight << std::endl;
std::cout << "Image channels: " << img.channels() << std::endl;
img.modifyImage();
for ( int row = 0; row <= imgHeight; row++ )
{
for ( int column = 0; column <= imgWidth; column++ )
{
ColorRGB px = img.pixelColor( column, row );
std::cout << "Pixel " << column << "," << row << " R: " << px.red() << " G: " << px.green() <<
" B: " << px.blue() << std::endl;
}
}
}
catch ( Magick::Exception & error )
{
std::cerr << "Caught Magick++ exception: " << error.what() << std::endl;
}
fin.close(); // Close the file
}