Related
I'm trying to count object from image. I use logs photo, and I use some steps to get a binary image.
This is my code:
#include <opencv2/core/core.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <iostream>
#include <features2d.hpp>
using namespace cv;
using namespace std;
int main(int argc, char *argv[])
{
//load image
Mat img = imread("kayu.jpg", CV_LOAD_IMAGE_COLOR);
if(img.empty())
return -1;
//namedWindow( "kayu", CV_WINDOW_AUTOSIZE );
imshow("kayu", img);
//convert to b/w
Mat bw;
cvtColor(img, bw, CV_BGR2GRAY);
imshow("bw1", bw);
threshold(bw, bw, 40, 255, CV_THRESH_BINARY);
imshow("bw", bw);
//distance transform & normalisasi
Mat dist;
distanceTransform(bw, dist, CV_DIST_L2, 3);
normalize(dist, dist, 0, 2., NORM_MINMAX);
imshow("dist", dist);
//threshold to draw line
threshold(dist, dist, .5, 1., CV_THRESH_BINARY);
imshow("dist2", dist);
//dist = bw;
//dilasi
Mat dilation, erotion, element;
int dilation_type = MORPH_ELLIPSE;
int dilation_size = 17;
element = getStructuringElement(dilation_type, Size(2*dilation_size + 1, 2*dilation_size+1), Point(dilation_size, dilation_size ));
erode(dist, erotion, element);
int erotionCount = 0;
for(int i=0; i<erotionCount; i++){
erode(erotion, erotion, element);
}
imshow("erotion", erotion);
dilate(erotion, dilation, element);
imshow("dilation", dilation);
waitKey(0);
return 0;
}
As you can see, I use Erosion and Dilation to get better circular object of log. My problem is, I'm stuck at counting the object. I tried SimpleBlobDetector but I got nothing, because when I try to convert the result of "dilation" step to CV_8U, the white object disappear. I got error too when I use findContours(). It say something about channel of image. I can't show the error here, because that's too many step and I already delete it from my code.
Btw, at the end, i got 1 channel of image.
Can i just use it to counting, or am i have to convert it and what is the best method to do it?
Two simple steps:
Find contours for the binarized image.
Get the count of the contours.
Code:
int count_trees(const cv::Mat& bin_image){
cv::Mat img;
if(bin_image.channels()>1){
cv::cvtColor(bin_image,img,cv::COLOR_BGR2GRAY);
}
else{
img=bin_image.clone();;
}
if(img.type()!=CV_8UC1){
img*=255.f; //This could be stupid, but I do not have an environment to try it
img.convertTo(img,CV_8UC1);
}
std::vector<std::vector<cv::Point>> contours
std::vector<Vec4i> hierarchy;
cv::findContours( img, contours, hierarchy, CV_RETR_EXTERNAL, CV_CHAIN_APPROX_SIMPLE);
return contours.size();
}
I have the same problem, here's an idea I'm about to implement.
1) Represent your image as an array of integers; 0 = black, 1 = white.
2) set N = 2;
3) Scan your image, pixel-by-pixel. Whenever you find a white pixel, activate a flood-fill algorithm, starting at the pixel just found; paint the region with the value of N++;
4) Iterate 3 until you reach the last pixel. (N-2) is the number of regions found.
This method depends on the shape of the objects; mine are more chaotic than yours (wish me luck..). I'll make use of a recursive flood-fill recipe found somewhere (maybe Rosetta Code).
This solution also makes it easy to compute the size of each region.
try to apply that on the your deleted img
// count
for (int i = 0; i< contours.size(); i = hierarchy[i][0]) // iteration sur chaque contour .
{
Rect r = boundingRect(contours[i]);
if (hierarchy[i][2]<0) {
rectangle(canny_output, Point(r.x, r.y), Point(r.x + r.width, r.y + r.height), Scalar(20, 50, 255), 3, 8, 0);
count++;
}
}
cout << "Numeber of contour = " << count << endl;
imshow("src", src);
imshow("contour", dst);
waitKey(0);
I'm currently working on a project that uses a Lacatan Banana, and I would like to know how to further separate the foreground from the background:
I already got a segmented image of it using erosion, dilation, and thresholding only. The problem is that it is still not properly segmented.
Here is my code:
cv::Mat imggray, imgthresh, fg, bgt, bg;
cv::cvtColor(src, imggray, CV_BGR2GRAY); //Grayscaling the image from RGB color space
cv::threshold(imggray, imgthresh, 0, 255, CV_THRESH_BINARY_INV | CV_THRESH_OTSU); //Create an inverted binary image from the grayscaled image
cv::erode(imgthresh, fg, cv::Mat(), cv::Point(-1, -1), 1); //erosion of the binary image and setting it as the foreground
cv::dilate(imgthresh, bgt, cv::Mat(), cv::Point(-1, -1), 4); //dilation of the binary image to reduce the background region
cv::threshold(bgt, bg, 1, 128, CV_THRESH_BINARY); //we get the background by setting the threshold to 1
cv::Mat markers = cv::Mat::zeros(src.size(), CV_32SC1); //initializing the markers with a size same as the source image and setting its data type as 32-bit Single channel
cv::add(fg, bg, markers); //setting the foreground and background as markers
cv::Mat mask = cv::Mat::zeros(markers.size(), CV_8UC1);
markers.convertTo(mask, CV_8UC1); //converting the 32-bit single channel marker to a 8-bit single channel
cv::Mat mthresh;
cv::threshold(mask, mthresh, 0, 255, CV_THRESH_BINARY | CV_THRESH_OTSU); //threshold further the mask to reduce the noise
// cv::erode(mthresh,mthresh,cv::Mat(), cv::Point(-1,-1),2);
cv::Mat result;
cv::bitwise_and(src, src, result, mthresh); //use the mask to subtrack the banana from the background
for (int x = 0; x < result.rows; x++) { //changing the black background to white
for (int y = 0; y < result.cols; y++) {
if (result.at<Vec3b>(x, y) == Vec3b(0, 0, 0)){
result.at<Vec3b>(x, y)[0] = 255;
result.at<Vec3b>(x, y)[1] = 255;
result.at<Vec3b>(x, y)[2] = 255;
}
}
}
This is my result:
As the background is near gray-color, try using Hue channel and Saturation channel instead of grayscale image.
You can get them easily.
cv::Mat hsv;
cv::cvtColor(src, hsv, CV_BGR2HSV);
std::vector<cv::Mat> channels;
cv::split(src, channels);
cv::Mat hue = channels[0];
cv::Mat saturation = channels[1];
// If you want to combine those channels, use this code.
cv::Mat hs = cv::Mat::zeros(src.size(), CV_8U);
for(int r=0; r<src.rows; r++) {
for(int c=0; c<src.cols; c++) {
int hp = h.at<uchar>(r,c);
int sp = s.at<uchar>(r,c);
hs.at<uchar>(r, c) = static_cast<uchar>((h+s)>>1);
}
}
adaptiveThreshold() should work better than just level-cut threshold(), because it does not consider absolute color levels, but rather a change in color in small area around the point being checked.
Try replacing your thresholding with adaptive one.
Use a top-hat instead of just erosion/dilation. It will take care of the background variations at the same time.
Then in your case a simple thresholding should be good enough to have an accurate segmentation. Else, you can couple it with a watershed.
(I will share some images asap).
Thanks guys, I tried to apply your advises and was able to come up with this
However as you can see there are still bits of the background,any ideas how to "clean" these further, i tried thresholding further but it would still have the bits.The Code I came up with is below and i apologize in advance if the variables and coding style is somewhat confusing didn't have the time to properly sort them.
#include <stdio.h>
#include <iostream>
#include <opencv2\core.hpp>
#include <opencv2\opencv.hpp>
#include <opencv2\highgui.hpp>
using namespace cv;
using namespace std;
Mat COLOR_MAX(Scalar(65, 255, 255));
Mat COLOR_MIN(Scalar(15, 45, 45));
int main(int argc, char** argv){
Mat src,hsv_img,mask,gray_img,initial_thresh;
Mat second_thresh,add_res,and_thresh,xor_thresh;
Mat result_thresh,rr_thresh,final_thresh;
// Load source Image
src = imread("sample11.jpg");
imshow("Original Image", src);
cvtColor(src,hsv_img,CV_BGR2HSV);
imshow("HSV Image",hsv_img);
//imwrite("HSV Image.jpg", hsv_img);
inRange(hsv_img,COLOR_MIN,COLOR_MAX, mask);
imshow("Mask Image",mask);
cvtColor(src,gray_img,CV_BGR2GRAY);
adaptiveThreshold(gray_img, initial_thresh, 255,ADAPTIVE_THRESH_GAUSSIAN_C,CV_THRESH_BINARY_INV,257,2);
imshow("AdaptiveThresh Image", initial_thresh);
add(mask,initial_thresh,add_res);
erode(add_res, add_res, Mat(), Point(-1, -1), 1);
dilate(add_res, add_res, Mat(), Point(-1, -1), 5);
imshow("Bitwise Res",add_res);
threshold(gray_img,second_thresh,170,255,CV_THRESH_BINARY_INV | CV_THRESH_OTSU);
imshow("TreshImge", second_thresh);
bitwise_and(add_res,second_thresh,and_thresh);
imshow("andthresh",and_thresh);
bitwise_xor(add_res, second_thresh, xor_thresh);
imshow("xorthresh",xor_thresh);
bitwise_or(and_thresh,xor_thresh,result_thresh);
imshow("Result image", result_thresh);
bitwise_and(add_res,result_thresh,final_thresh);
imshow("Final Thresh",final_thresh);
erode(final_thresh, final_thresh, Mat(), Point(-1,-1),5);
bitwise_and(src,src,rr_thresh,final_thresh);
imshow("Segmented Image", rr_thresh);
imwrite("Segmented Image.jpg", rr_thresh);
waitKey(0);
return 1;
}
friends, could you please help with my questions?
I am using opencv in c++.
I am randomly cropping a small picture from a camera view. I want to find the word located at the bottom of this cropped picture, and this word should also be penetrated by the vertical center line (imaginary) of this cropped picture. please see the following code :
char* my_word = do_ocr(my_cropped_image);
and the do_ocr function is like this:
char* do_ocr(cv::Mat im)
{
cv::Mat gray;
cv::cvtColor(im, gray, CV_BGR2GRAY);
// ...other image pre-processing here...
// Pass it to Tesseract API
tesseract::TessBaseAPI tess;
tess.Init(NULL, "eng", tesseract::OEM_DEFAULT);
tess.SetPageSegMode(tesseract::PSM_SINGLE_BLOCK);
tess.SetImage((uchar*)gray.data, gray.cols, gray.rows, 1, gray.cols);
// Get the text
char* out = tess.GetUTF8Text();
std::cout << out << std::endl;
return out;
}
The following is the schematic diagram and some samples of my_cropped_image :
my_cropped_image sample # 1, the letter "preceding" should be detected:
my_cropped_image sample # 2, the letter "advantageous" should be detected:
my_cropped_image sample # 3, the letter "Correlation" should be detected:
my_cropped_image sample # 4, the letter "density" should be detected:
my_cropped_image sample # 5, the letter "time" should be detected:
I'll appreciate the helps from you to update my do_ocr function.
Thank you and have a great day!
Are these the results you were looking for?
Methodology:
1) Binaryze the image, white is foreground. Here is simply done with img = img < 150;. You can use more sophisticated methods, like adaptiveThreshold.
You get something like:
2) Apply a open morphological operation, so that all the letters in a single word for a single blob:
3) Find the rectangle of each connected component:
4) Take the bottom one, in the center.
Here the full code:
#include <opencv2\opencv.hpp>
#include <vector>
using namespace std;
using namespace cv;
Mat3b dbg;
int main()
{
Mat1b img = imread("path_to_image", IMREAD_GRAYSCALE);
cvtColor(img, dbg, COLOR_GRAY2BGR);
Mat3b result;
cvtColor(img, result, COLOR_GRAY2BGR);
Mat1b img2;
img2 = img < 150;
Mat kernel = getStructuringElement(MORPH_ELLIPSE, Size(5,3));
morphologyEx(img2, img2, MORPH_DILATE, kernel);
// Apply a small border
copyMakeBorder(img2, img2, 5, 5, 5, 5, BORDER_CONSTANT, Scalar(0));
// Take the bounding boxes of all connected components
vector<vector<Point>> contours;
findContours(img2.clone(), contours, CV_RETR_LIST, CHAIN_APPROX_NONE);
int minArea = 60;
vector<Rect> rects;
for (int i = 0; i < contours.size(); ++i)
{
Rect r = boundingRect(contours[i]);
if (r.area() >= minArea)
{
// Account for border
r -= Point(5,5);
rects.push_back(r);
}
}
int middle = img.cols / 2;
// Keep bottom rect, containig middle point
if (rects.empty()) return -1;
Rect word;
for (int i = 1; i < rects.size(); ++i)
{
Point pt(middle, rects[i].y + rects[i].height/2);
if (rects[i].contains(pt))
{
if (rects[i].y > word.y)
{
word = rects[i];
}
}
}
// Show results
Mat3b res;
cvtColor(img, res, COLOR_GRAY2BGR);
for (int i = 0; i < rects.size(); ++i)
{
rectangle(res, rects[i], Scalar(0, 255, 0));
}
rectangle(result, word, Scalar(0, 0, 255), 2);
imshow("Rects", res);
imshow("Result", result);
waitKey();
return 0;
}
I'm writing a program using opencv that does text detection and extraction.
Im using the Sobel derivative in order to do edge detection and have gotten the following result:
But I wish to get the following result:
(I appologize for the blurry image.)
The problem I'm having is the "blank areas" inside the edges "confuse" the algorithem I'm using so when the algorithem detects the "blank part" seperating between two lines from the lines themselves it gets confused and start running into the letter themselves instead of keepeing between two lines. This error, I believe would be solves by achieving the second result.
Anyone knows what changes i need to make? in the soble derivative? maybe use a different derivative?
Code:
Mat ProfileSeamTextLineExtractor::computeDerivative(){
Mat img = _image;
Mat gradiant_mat;
int scale = 2;
int delta = 0;
int ddepth = CV_16S;
GaussianBlur(img, img, Size(3, 3), 0, 0, BORDER_DEFAULT);
Mat grad_x, grad_y;
Mat abs_grad_x, abs_grad_y;
Sobel(img, grad_x, ddepth, 1, 0, 3, scale, delta, BORDER_DEFAULT);
convertScaleAbs(grad_x, abs_grad_x);
Sobel(img, grad_y, ddepth, 0, 1, 3, scale, delta, BORDER_DEFAULT);
convertScaleAbs(grad_y, abs_grad_y);
/// Total Gradient (approximate)
addWeighted(abs_grad_x, 0.5, abs_grad_y, 0.5, 0, gradiant_mat);
return gradiant_mat;
}
Regards,
Try using the second sobel derivative, add, normalize (this may do the same as addWeighted), and then thresholding optimally. I had results similar to yours with different threshold values.
Here's an example:
cv::Mat result;
cvtColor(image, gray, CV_BGR2GRAY);
cv::medianBlur(gray, gray, 3);
cv::Mat sobel_x, sobel_y, result;
cv::Sobel(gray, sobel_x, CV_32FC1, 2, 0, 5);
cv::Sobel(gray, sobel_y, CV_32FC1, 0, 2, 5);
cv::Mat sum = sobel_x + sobel_y;
cv::normalize(sum, result, 0, 255, CV_MINMAX, CV_8UC1);
//Determine optimal threshold value using THRESH_OTSU.
// This didn't give me optimal results, but was a good starting point.
cv::Mat temp, final;
double threshold = cv::threshold(result, temp, 0, 255, CV_THRESH_BINARY+CV_THRESH_OTSU);
cv::threshold(result, final, threshold*.9, 255, CV_THRESH_BINARY);
I was able to clearly extract both light text on a dark background, and dark text on a light background.
If you need the final image to consistently be white background with black text, you can do this:
cv::Scalar avgPixelIntensity = cv::mean( final );
if(avgPixelIntensity[0] < 127.0)
cv::bitwise_not(final, final);
I tried a lot of different text extraction methods and couldn't find any that worked across the board, but this seems to. This took a lot of trial and error to figure out, so I hope this helps.
I don't really understand what your final aim is. Do you eventually want a nice filled in version of the text so you can recognise the characters? I can give that a shot if that's what you are looking for.
This is what I did while trying to remove inner holes:
For this one I didn't bother:
It fails at the edges where the text is cut off.
Obviously, I had to work with the image that had already gone through some processing. I might be able to give you more help if I had the original and produce a better output. You might not even need to use derivatives at all if the background is clean enough.
Here is the code:
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <iostream>
using namespace cv;
using namespace std;
void printInnerContours (int contourPos, Mat &filled, vector<vector<Point2i > > &contours, vector<Vec4i> &hierarchy, int area);
int main() {
int areaThresh;
vector<vector<Point2i > > contours;
vector<Vec4i> hierarchy;
Mat text = imread ("../wHWHA.jpg", 0); //write greyscale
threshold (text, text, 50, 255, THRESH_BINARY);
imwrite ("../text1.jpg", text);
areaThresh = (0.01 * text.rows * text.cols) / 100;
findContours (text, contours, hierarchy, CV_RETR_TREE, CV_CHAIN_APPROX_NONE);
Mat filled = Mat::zeros(text.rows, text.cols, CV_8U);
cout << contours.size() << endl;
for (int i = 0; i < contours.size(); i++) {
int area = contourArea(contours[i]);
if (area > areaThresh) {
if ((hierarchy[i][2] != -1) && (hierarchy[i][3] == -1)) {
drawContours (filled, contours, i, 255, -1);
if (hierarchy[i][2] != -1) {
printInnerContours (hierarchy[i][2], filled, contours, hierarchy, area);
}
}
}
}
imwrite("../output.jpg", filled);
return 0;
}
void printInnerContours (int contourPos, Mat &filled, vector<vector<Point2i > > &contours, vector<Vec4i> &hierarchy, int area) {
int areaFrac = 5;
if (((contourArea (contours[contourPos]) * 100) / area) < areaFrac) {
//drawContours (filled, contours, contourPos, 0, -1);
}
if (hierarchy[contourPos][2] != -1) {
printInnerContours (hierarchy[contourPos][2], filled, contours, hierarchy, area);
}
if (hierarchy[contourPos][0] != -1) {
printInnerContours (hierarchy[contourPos][0], filled, contours, hierarchy, area);
}
}
I am trying to detect some lines using Hough Transform on a cv::gpu::GpuMat structure. I have tried using both gpu::HoughLines and gpu::HoughLinesP but even with extremely low thresholds, I am not getting any results at all. During debugging, I see that the container which should contain the results (houghLines) has only zeros stored inside it. The code I have written is given below,
static cv::Mat drawHoughLinesOnMat (cv::gpu::GpuMat hough_Mat, cv::gpu::GpuMat houghLines)
{
cv::Mat output_Mat;
cv::cvtColor(cv::Mat(hough_Mat), output_Mat, CV_GRAY2BGR);
std::vector<cv::Vec4i> lines_vector;
if (!houghLines.empty())
{
lines_vector.resize(houghLines.cols);
cv::Mat temp_Mat (1, houghLines.cols, CV_8UC3, &lines_vector[0]);
houghLines.download (temp_Mat);
}
for (size_t i=0; i<lines_vector.size(); ++i)
{
cv::Vec4i l = lines_vector[i];
cv::line(output_Mat, cv::Point(l[0], l[1]), cv::Point(l[2], l[3]), cv::Scalar(0, 0, 255), 1, 8);
}
return output_Mat;
}
int main()
{
cv::Mat input = cv::imread(INPUT_DATA_1->c_str(), CV_LOAD_IMAGE_GRAYSCALE);
std::string imageType = getImgType(input.type());
cv::gpu::GpuMat mat_input(input), bil_out, mat_thresh, hough_lines;
cv::gpu::HoughLinesBuf hough_buffer;
int bilateral_thresh = 15; // 5 == 0.085s; 15 == 0.467s at run-time
cv::gpu::bilateralFilter(mat_input, bil_out, bilateral_thresh, bilateral_thresh*2, bilateral_thresh/2);
//cv::gpu::threshold(bil_out, mat_thresh, 10, 255, CV_THRESH_BINARY);
cv::gpu::Canny(bil_out, mat_thresh, 10, 60, 5);
cv::gpu::HoughLinesP(mat_thresh, hough_lines, hough_buffer, 1.0f, (float)(CV_PI/180.0f), 5, 1);
//cv::Mat test_hough(hough_lines);
cv::Mat hough_Mat = drawHoughLinesOnMat(mat_input, hough_lines);
cv::gpu::HoughLines(mat_thresh, hough_lines, 1.0f, (float)(CV_PI/180.0f), 1, true);
/*cv::Mat */hough_Mat = drawHoughLinesOnMat(mat_input, hough_lines);
return EXIT_SUCCESS
}
The image I am using is,
Could someone tell me what it is that I am doing wrong..? Thanks in advance.!
The output of the Canny filter is,
EDIT:
I have tested on the CPU version of HoughLines and it seems to work just fine.
EDIT_2:
The solution posted by #jet47 works perfectly.
You use incorrect code for downloading results from GPU back to CPU:
lines_vector.resize(houghLines.cols);
cv::Mat temp_Mat (1, houghLines.cols, CV_8UC3, &lines_vector[0]);
houghLines.download (temp_Mat);
You use incorrect type for temp_Mat - CV_8UC3, it must be CV_32SC4.
The correct code is:
lines_vector.resize(houghLines.cols);
cv::Mat temp_Mat(1, houghLines.cols, CV_32SC4, &lines_vector[0]);
houghLines.download(temp_Mat);
My guess is that the Method you are using is outdated (but im not entirely sure).
This is how i would do it(as demonstrated in this Example Code):
//d_src filled with your image somewhere
GpuMat d_lines;
{
Ptr<cuda::HoughSegmentDetector> hough = cuda::createHoughSegmentDetector(1.0f, (float) (CV_PI / 180.0f), 50, 5);
hough->detect(d_src, d_lines);
}
vector<Vec4i> lines_gpu;
if (!d_lines.empty())
{
lines_gpu.resize(d_lines.cols);
Mat h_lines(1, d_lines.cols, CV_32SC4, &lines_gpu[0]);
d_lines.download(h_lines);
}
for (size_t i = 0; i < lines_gpu.size(); ++i)
{
Vec4i l = lines_gpu[i];
line(dst_gpu, Point(l[0], l[1]), Point(l[2], l[3]), Scalar(0, 0, 255), 3, LINE_AA);
}
EDIT The above uses the OpenCv 3.0 Interface