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;
}
Related
I'm new to image processing and development. I need to take the inside triangle pixels of the image. In order to do it I used the following code. Unfortunately I obtain unwanted black pixels. get rid of that problem i tried to remove background[0] pixels by giving alfa value.(tranparent background) But it gives following Error. Any help is appreciated.
My code:
Mat img = cv::imread("/home/fabio/code/lena.jpg", cv::IMREAD_GRAYSCALE);
Mat alpha(img.size(), CV_8UC1, Scalar(0));
//triangle definition (example points)
vector<Point> points;
points.push_back(Point(200, 70));
points.push_back(Point(60, 150));
points.push_back(Point(500, 500));
//apply triangle to mask
fillConvexPoly(alpha, points, Scalar(255));
cv::Mat finalImage = cv::Mat::zeros(img.size(), img.type());
img.copyTo(finalImage, alpha);
imshow("image", finalImage);
Mat dst;
Mat rgb[1];
split(finalImage, rgb);
Mat rgba[2] = { finalImage, alpha };
merge(rgba, 2, dst);
imshow("dst", dst);
Error: OpenCV Error: Bad number of channels (Source image must have 1, 3 or 4 channels) in cvConvertImage, file C:\builds\2_4_PackSlave-win64-vc12-shared\opencv\modules\highgui\src\utils.cpp, line 611
use this instead of your last block:
std::vector<cv::Mat> channels;
cv::split(finalImage,m channels);
if(channels.size() == 0)
{
std::cout << "unexpected error" << std::endl;
return 1;
}
// fill up to reach 3 channels
while(channels,size() < 3)
{
channels.push_back(channels[0]);
}
// add alpha channel
channels.push_back(alpha);
cv::merge(channels, dst);
I didn't test it but this should be what you want?
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 have a question which i am unable to resolve. I am taking difference of two images using OpenCV. I am getting output in a seperate Mat. Difference method used is the AbsDiff method. Here is the code.
char imgName[15];
Mat img1 = imread(image_path1, COLOR_BGR2GRAY);
Mat img2 = imread(image_path2, COLOR_BGR2GRAY);
/*cvtColor(img1, img1, CV_BGR2GRAY);
cvtColor(img2, img2, CV_BGR2GRAY);*/
cv::Mat diffImage;
cv::absdiff(img2, img1, diffImage);
cv::Mat foregroundMask = cv::Mat::zeros(diffImage.rows, diffImage.cols, CV_8UC3);
float threshold = 30.0f;
float dist;
for(int j=0; j<diffImage.rows; ++j)
{
for(int i=0; i<diffImage.cols; ++i)
{
cv::Vec3b pix = diffImage.at<cv::Vec3b>(j,i);
dist = (pix[0]*pix[0] + pix[1]*pix[1] + pix[2]*pix[2]);
dist = sqrt(dist);
if(dist>threshold)
{
foregroundMask.at<unsigned char>(j,i) = 255;
}
}
}
sprintf(imgName,"D:/outputer/d.jpg");
imwrite(imgName, diffImage);
I want to bound the difference part in a rectangle. findContours is drawing too many contours. but i only need a particular portion. My diff image is
I want to draw a single rectangle around all the five dials.
Please point me to right direction.
Regards,
I would search for the highest value for i index giving a non black pixel; that's the right border.
The lowest non black i is the left border. Similar for j.
You can:
binarize the image with a threshold. Background will be 0.
Use findNonZero to retrieve all points that are not 0, i.e. all foreground points.
use boundingRect on the retrieved points.
Result:
Code:
#include <opencv2/opencv.hpp>
using namespace cv;
int main()
{
// Load image (grayscale)
Mat1b img = imread("path_to_image", IMREAD_GRAYSCALE);
// Binarize image
Mat1b bin = img > 70;
// Find non-black points
vector<Point> points;
findNonZero(bin, points);
// Get bounding rect
Rect box = boundingRect(points);
// Draw (in color)
Mat3b out;
cvtColor(img, out, COLOR_GRAY2BGR);
rectangle(out, box, Scalar(0,255,0), 3);
// Show
imshow("Result", out);
waitKey();
return 0;
}
Find contours, it will output a set of contours as std::vector<std::vector<cv::Point> let us call it contours:
std::vector<cv::Point> all_points;
size_t points_count{0};
for(const auto& contour:contours){
points_count+=contour.size();
all_points.reserve(all_points);
std::copy(contour.begin(), contour.end(),
std::back_inserter(all_points));
}
auto bounding_rectnagle=cv::boundingRect(all_points);
I am processing video images and I would like to detect if the video contains any pixels of a certain range of red. Is this possible?
Here is the code I am adapting from a tutorial:
#ifdef __cplusplus
- (void)processImage:(Mat&)image;
{
cv::Mat orig_image = image.clone();
cv::medianBlur(image, image, 3);
cv::Mat hsv_image;
cv::cvtColor(image, hsv_image, cv::COLOR_BGR2HSV);
cv::Mat lower_red_hue_range;
cv::Mat upper_red_hue_range;
cv::inRange(hsv_image, cv::Scalar(0, 100, 100), cv::Scalar(10, 255, 255), lower_red_hue_range);
cv::inRange(hsv_image, cv::Scalar(160, 100, 100), cv::Scalar(179, 255, 255), upper_red_hue_range);
// Interpret values here
}
Interpreting values
I would like to detect if the results from the inRange operations are nil or not. In other words I want to understand if there are any matching pixels in the original image with a colour inRange from the given lower and upper red scale. How can I interpret the results?
First you need to OR the lower and upper mask:
Mat mask = lower_red_hue_range | upper_red_hue_range;
Then you can countNonZero to see if there are non zero pixels (i.e. you found something).
int number_of_non_zero_pixels = countNonZero(mask);
It could be better to first apply morphological erosion or opening to remove small (probably noisy) blobs:
Mat kernel = getStructuringElement(MORPH_ELLIPSE, Size(3, 3));
morphologyEx(mask, mask, MORPH_OPEN, kernel); // or MORPH_ERODE
or find connected components (findContours, connectedComponentsWithStats) and prune / search for according to some criteria:
vector<vector<Point>> contours
findContours(mask.clone(), contours, RETR_EXTERNAL, CHAIN_APPROX_SIMPLE);
double threshold_on_area = 100.0;
for(int i=0; i<contours.size(); ++i)
{
double area = countourArea(contours[i]);
if(area < threshold_on_area)
{
// don't consider this contour
continue;
}
else
{
// do something (e.g. drawing a bounding box around the contour)
Rect box = boundingRect(contours[i]);
rectangle(hsv_image, box, Scalar(0, 255, 255));
}
}
I am a beginner in OpenCV, I need to remove the horizontal and vertical lines in the image so that only the text remains ( The lines were causing trouble when extracting text in ocr ). I am trying to extract text from the Nutrient Fact Table. Can anyone help me?
This was an interesting question, so I gave it a shot. Below I will show you how to extract and remove horizontal and vertical lines. You could extrapolate from it. Also, for sake of saving time, I did not preprocess your image to crop out the background as one should, which is an avenue for improvement.
The result:
The code (edit: added vertical lines):
#include <iostream>
#include <opencv2/opencv.hpp>
using namespace std;
using namespace cv;
int main(int, char** argv)
{
// Load the image
Mat src = imread(argv[1]);
// Check if image is loaded fine
if(!src.data)
cerr << "Problem loading image!!!" << endl;
Mat gray;
if (src.channels() == 3)
{
cvtColor(src, gray, CV_BGR2GRAY);
}
else
{
gray = src;
}
//inverse binary img
Mat bw;
//this will hold the result, image to be passed to OCR
Mat fin;
//I find OTSU binarization best for text.
//Would perform better if background had been cropped out
threshold(gray, bw, 0, 255, THRESH_BINARY_INV | THRESH_OTSU);
threshold(gray, fin, 0, 255, THRESH_BINARY | THRESH_OTSU);
imshow("binary", bw);
Mat dst;
Canny( fin, dst, 50, 200, 3 );
Mat str = getStructuringElement(MORPH_RECT, Size(3,3));
dilate(dst, dst, str, Point(-1, -1), 3);
imshow("dilated_canny", dst);
//bitwise_and w/ canny image helps w/ background noise
bitwise_and(bw, dst, dst);
imshow("and", dst);
Mat horizontal = dst.clone();
Mat vertical = dst.clone();
fin = ~dst;
//Image that will be horizontal lines
Mat horizontal = bw.clone();
//Selected this value arbitrarily
int horizontalsize = horizontal.cols / 30;
Mat horizontalStructure = getStructuringElement(MORPH_RECT, Size(horizontalsize,1));
erode(horizontal, horizontal, horizontalStructure, Point(-1, -1));
dilate(horizontal, horizontal, horizontalStructure, Point(-1, -1), 1);
imshow("horizontal_lines", horizontal);
//Need to find horizontal contours, so as to not damage letters
vector<Vec4i> hierarchy;
vector<vector<Point> >contours;
findContours(horizontal, contours, hierarchy, CV_RETR_TREE, CV_CHAIN_APPROX_NONE);
for (const auto& c : contours)
{
Rect r = boundingRect(c);
float percentage_height = (float)r.height / (float)src.rows;
float percentage_width = (float)r.width / (float)src.cols;
//These exclude contours that probably are not dividing lines
if (percentage_height > 0.05)
continue;
if (percentage_width < 0.50)
continue;
//fills in line with white rectange
rectangle(fin, r, Scalar(255,255,255), CV_FILLED);
}
int verticalsize = vertical.rows / 30;
Mat verticalStructure = getStructuringElement(MORPH_RECT, Size(1,verticalsize));
erode(vertical, vertical, verticalStructure, Point(-1, -1));
dilate(vertical, vertical, verticalStructure, Point(-1, -1), 1);
imshow("verticalal", vertical);
findContours(vertical, contours, hierarchy, CV_RETR_TREE, CV_CHAIN_APPROX_NONE);
for (const auto& c : contours)
{
Rect r = boundingRect(c);
float percentage_height = (float)r.height / (float)src.rows;
float percentage_width = (float)r.width / (float)src.cols;
//These exclude contours that probably are not dividing lines
if (percentage_width > 0.05)
continue;
if (percentage_height < 0.50)
continue;
//fills in line with white rectange
rectangle(fin, r, Scalar(255,255,255), CV_FILLED);
}
imshow("Result", fin);
waitKey(0);
return 0;
}
The limitations of this approach are that the lines need to be straight. Due to the curve in the bottom line, it cuts slightly into "E" in "Energy". Perhaps with a hough line detection like suggested (I've never used it), a similar but more robust approach could be devised. Also, filling in the lines with rectangles probably is not the best approach.