Skew angle detection on a image with scattered characters - c++

I've been following this tutorial to get the skew angle of an image. It seems like HoughLinesP is struggling to find lines when characters are a bit scattered on the target image.
This is my input image:
This is the lines the HoughLinesP has found:
It's not really getting most of the lines and it seems pretty obvious to me why. This is because I've set my minLineWidth to be (size.width / 2.f). The point is that because of the few lines it has found it turns out that the skew angle is also wrong. (-3.15825 in this case, when it should be something close to 0.5)
I've tried to erode my input file to make characters get closer and in this case it seems to work out, but I don't feel this is best approach for situations akin to it.
This is my eroded input image:
This is the lines the HoughLinesP has found:
This time it has found a skew angle of -0.2185 degrees, which is what I was expecting but in other hand it is losing the vertical space between lines which in my humble opinion isn't a good thing.
Is there another to pre-process this kind of image to make houghLinesP get better results for scattered characters ?
Here is the source code I'm using:
#include <iostream>
#include <opencv2/opencv.hpp>
using namespace std;
static cv::Scalar randomColor( cv::RNG& rng )
{
int icolor = (unsigned) rng;
return cv::Scalar( icolor&255, (icolor>>8)&255, (icolor>>16)&255 );
}
void rotate(cv::Mat& src, double angle, cv::Mat& dst)
{
int len = std::max(src.cols, src.rows);
cv::Point2f pt(len/2., len/2.);
cv::Mat r = cv::getRotationMatrix2D(pt, angle, 1.0);
cv::warpAffine(src, dst, r, cv::Size(len, len));
}
double compute_skew(cv::Mat& src)
{
// Random number generator
cv::RNG rng( 0xFFFFFFFF );
cv::Size size = src.size();
cv::bitwise_not(src, src);
std::vector<cv::Vec4i> lines;
cv::HoughLinesP(src, lines, 1, CV_PI/180, 100, size.width / 2.f, 20);
cv::Mat disp_lines(size, CV_8UC3, cv::Scalar(0, 0, 0));
double angle = 0.;
unsigned nb_lines = lines.size();
for (unsigned i = 0; i < nb_lines; ++i)
{
cv::line(disp_lines, cv::Point(lines[i][0], lines[i][1]),
cv::Point(lines[i][2], lines[i][3]), randomColor(rng));
angle += atan2((double)lines[i][3] - lines[i][1],
(double)lines[i][2] - lines[i][0]);
}
angle /= nb_lines; // mean angle, in radians.
std::cout << angle * 180 / CV_PI << std::endl;
cv::imshow("HoughLinesP", disp_lines);
cv::waitKey(0);
return angle * 180 / CV_PI;
}
int main()
{
// Load in grayscale.
cv::Mat img = cv::imread("IMG_TESTE.jpg", 0);
cv::Mat rotated;
double angle = compute_skew(img);
rotate(img, angle, rotated);
//Show image
cv::imshow("Rotated", rotated);
cv::waitKey(0);
}
Cheers

I'd suggest finding individual components first (i.e., the lines and the letters), for example using cv::threshold and cv::findContours.
Then, you could drop the individual components that are narrow (i.e., the letters). You can do this using cv::floodFill for example. This should leave you with the lines only.
Effectively, getting rid of the letters might provide easier input for the Hough transform.

Try to detect groups of characters as blocks, then find contours of these blocks. Below I've done it using blurring, a morphological opening and a threshold operation.
Mat im = imread("yCK4t.jpg", 0);
Mat blurred;
GaussianBlur(im, blurred, Size(5, 5), 2, 2);
Mat kernel = getStructuringElement(MORPH_ELLIPSE, Size(3, 3));
Mat morph;
morphologyEx(blurred, morph, CV_MOP_OPEN, kernel);
Mat bw;
threshold(morph, bw, 0, 255, CV_THRESH_BINARY_INV | CV_THRESH_OTSU);
Mat cont = Mat::zeros(im.rows, im.cols, CV_8U);
vector<vector<Point>> contours;
vector<Vec4i> hierarchy;
findContours(bw, contours, hierarchy, CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE, Point(0, 0));
for(int idx = 0; idx >= 0; idx = hierarchy[idx][0])
{
drawContours(cont, contours, idx, Scalar(255, 255, 255), 1);
}
Then use Hough line transform on contour image.
With accumulator threshold 80, I get following lines that results in an angle of -3.81. This is high because of the outlier line that is almost vertical. With this approach, majority of the lines will have similar angle values except few outliers. Detecting and discarding the outliers will give you a better approximation of the angle.
HoughLinesP(cont, lines, 1, CV_PI/180, 80, size.width / 4.0f, size.width / 8.0f);

Related

How to count white object on Binary Image?

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);

OpenCV: how can I interpret the results of inRange?

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));
}
}

Removing lines from image

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.

Lines and edges detector, opencv

I'm trying to process the following images from a maze. My Question is about how to process the edges. I'm using OpenCV 2.4 with c++.
I'd like to know if there is any way to discriminate the edges between the floor and the wall from the lines painted in the floor?
The floor is black, the walls are white and the lines painted in the floor are white too.
What I am trying to do is distinguish between wall and marks in floor. The lines on the floor will give me a distance reference and if I can turn in the maze. While the walls just tell the limit of the halls of the maze.
here you'll find the process images I've done.
I'm using Canny and HoughLinesP functions to detect and save the lines. But as you can see in the images the program doesn't separate the lines from the edges.
The code:
vector<Vec4i> get_lines(Mat dst, Mat cdst)
{
vector<Vec4i> lines;
HoughLinesP(dst, lines, 1, CV_PI/180, 100, 50, 10 );
for( size_t i = 0; i < lines.size(); i++ )
{
Vec4i l = lines[i];
double size = norm(Mat(Point(l[0], l[1])), Mat(Point(l[2], l[3])) );
if(size > 100)
line( cdst, Point(l[0], l[1]), Point(l[2], l[3]), Scalar(0,0,255), 3, CV_AA);
}
return lines;
}
And main function is:
int main(int argc, char** argv)
{
const char* filename = argc >= 2 ? argv[1] : "pic1.jpg";
Mat src = imread(filename, 0);
if(src.empty())
{
help();
cout << "can not open " << filename << endl;
return -1;
}
Mat dst, cdst;
Canny(src, dst, 50, 200, 3);
cvtColor(dst, cdst, CV_GRAY2BGR);
vector<Vec4i> lines = get_lines(dst, cdst);
imshow("source W&B", src);
imshow("edges", dst);
imshow("detected lines", cdst);
imwrite("lines.jpg",cdst);
imwrite("src.jpg",src);
imwrite("canny.jpg",dst);
waitKey();
return 0;
}
The obvious thing to try would be to compare the brightness of pixels on either side of the line.
make three regions: pixels a little distance to one side of the line, pixels a little distance to the other side of the line, and pixels close to the line. Calculate the average brightness in either region.
The walls are light grey, the floor is black and the lines are white, so
if one side is significantly brighter than the other side, it is probably an edge (and you can even tell which side is the floor),
if both sides are significantly darker than the middle it is probably a marking on the floor.
(and if the line is vertical, it is a wall-wall edge)

Derivatives in OpenCV

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);
}
}