Extracting text from an image OpenCV

edit

My goal is to extract the nutrient information of a food product. The image is taken from a phone camera and cropped to the Nutrient Fact table.

I have performed some preprocessing to obtain an enhanced image like this

I followed the steps to extract the text from the link https://github.com/Itseez/opencv_cont...

I got this result for the decomposed image

And finally the detected text

The terminal output

Code :

#include <iostream>
#include "opencv2/text.hpp"
#include <opencv2/opencv.hpp>
#include <tesseract/baseapi.h>
#include <tesseract/strngs.h>

using namespace std;
using namespace cv;
using namespace cv::text;

bool isRepetitive(const string& s){
    int count = 0;

    for (int i=0; i<(int)s.size(); i++){
        if ((s[i] == 'i') ||
                (s[i] == 'l') ||
                (s[i] == 'I'))
            count++;
    }
    if (count > ((int)s.size()+1)/2){
        return true;
    }
    return false;
}

void er_draw(vector<Mat> &channels, vector<vector<ERStat> > &regions, vector<Vec2i> group, Mat& segmentation){

    for (int r=0; r<(int)group.size(); r++){
        ERStat er = regions[group[r][0]][group[r][1]];
        if (er.parent != NULL) { // deprecate the root region
            int newMaskVal = 255;
            int flags = 4 + (newMaskVal << 8) + FLOODFILL_FIXED_RANGE + FLOODFILL_MASK_ONLY;
            floodFill(channels[group[r][0]],segmentation,Point(er.pixel%channels[group[r][0]].cols,er.pixel/channels[group[r][0]].cols),
                      Scalar(255),0,Scalar(er.level),Scalar(0),flags);
        }
    }
}

std::vector<Mat> extractTableFromImage(Mat src){

    // resizing for practical reasons
    Mat rsz;
    Size size(800, 900);
    resize(src, rsz, size);

    // Transform source image to gray if it is not and show grayscale image
    Mat gray;
    if (rsz.channels() == 3){
        cvtColor(rsz, gray, CV_BGR2GRAY);
    } else {
        gray = rsz;
    }

    // Apply adaptiveThreshold at the bitwise_not of gray, notice the ~ symbol
    Mat bw;
    adaptiveThreshold(~gray, bw, 255, CV_ADAPTIVE_THRESH_MEAN_C, THRESH_BINARY, 15, -2);

    // Create the images that will use to extract the horizontal and vertical lines
    Mat horizontal = bw.clone();
    Mat vertical = bw.clone();

    int scale = 20; // change this variable in order to increase/decrease the amount of lines to be detected

    // Specify size on horizontal axis
    int horizontalsize = horizontal.cols / scale;
    // Create structure element for extracting horizontal lines through morphology operations
    Mat horizontalStructure = getStructuringElement(MORPH_RECT, Size(horizontalsize,1));
    // Apply morphology operations, erosion removes white noises, but it also shrinks our object
    //So we dilate it, since noise is gone, they won't come back, but our object area increases
    erode(horizontal, horizontal, horizontalStructure, Point(-1, -1));
    dilate(horizontal, horizontal, horizontalStructure, Point(-1, -1));

    // Specify size on vertical axis
    int verticalsize = vertical.rows / scale;
    // Create structure element for extracting vertical lines through morphology operations
    Mat verticalStructure = getStructuringElement(MORPH_RECT, Size( 1,verticalsize));
    // Apply morphology operations
    erode(vertical, vertical, verticalStructure, Point(-1, -1));
    dilate(vertical, vertical, verticalStructure, Point(-1, -1));

    // create a mask which includes the tables
    Mat mask = horizontal + vertical;

    // find the joints between the lines of the tables, we will use this information in order
    // to descriminate tables from pictures
    Mat joints;
    bitwise_and(horizontal, vertical, joints);

    // Find external contours from the mask, which most probably will belong to tables or to images
    vector<Vec4i> hierarchy;
    std::vector<std ...