I need to recognize text in an image and then crop out the rectangle with the text to reduce the image size
The first step is to recognize the text and I have found a solution here
But how to compile and run this from PHP? I'm not familiar with C
How to compile the code so you can pass arguments to the program like exec('opencv_test input.jpg output.jpg')
Instead of drawing rectangles around each text block the program should analyse all text blocks and get the two coordinates where the image should be cropped.. And then crop the image an write the output file to the output destination
code
#include "stdafx.h"
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <iostream>
using namespace cv;
using namespace std;
#define INPUT_FILE "1.jpg"
#define OUTPUT_FOLDER_PATH string("")
int _tmain(int argc, _TCHAR* argv[])
{
Mat large = imread(INPUT_FILE);
Mat rgb;
// downsample and use it for processing
pyrDown(large, rgb);
Mat small;
cvtColor(rgb, small, CV_BGR2GRAY);
// morphological gradient
Mat grad;
Mat morphKernel = getStructuringElement(MORPH_ELLIPSE, Size(3, 3));
morphologyEx(small, grad, MORPH_GRADIENT, morphKernel);
// binarize
Mat bw;
threshold(grad, bw, 0.0, 255.0, THRESH_BINARY | THRESH_OTSU);
// connect horizontally oriented regions
Mat connected;
morphKernel = getStructuringElement(MORPH_RECT, Size(9, 1));
morphologyEx(bw, connected, MORPH_CLOSE, morphKernel);
// find contours
Mat mask = Mat::zeros(bw.size(), CV_8UC1);
vector<vector<Point>> contours;
vector<Vec4i> hierarchy;
findContours(connected, contours, hierarchy, CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE, Point(0, 0));
// filter contours
for(int idx = 0; idx >= 0; idx = hierarchy[idx][0])
{
Rect rect = boundingRect(contours[idx]);
Mat maskROI(mask, rect);
maskROI = Scalar(0, 0, 0);
// fill the contour
drawContours(mask, contours, idx, Scalar(255, 255, 255), CV_FILLED);
// ratio of non-zero pixels in the filled region
double r = (double)countNonZero(maskROI)/(rect.width*rect.height);
if (r > .45 /* assume at least 45% of the area is filled if it contains text */
&&
(rect.height > 8 && rect.width > 8) /* constraints on region size */
/* these two conditions alone are not very robust. better to use something
like the number of significant peaks in a horizontal projection as a third condition */
)
{
rectangle(rgb, rect, Scalar(0, 255, 0), 2);
}
}
imwrite(OUTPUT_FOLDER_PATH + string("rgb.jpg"), rgb);
return 0;
}