Software that identifies letters does so by comparing text with previously recorded data. Classification results can be improved greatly if the input text is clear, if the letters are in a vertical position, and if there's no other elements, such as images sent to the classification software. In this section, we'll learn how to adjust text by using preprocessing.
We usually start preprocessing by thresholding the image. This eliminates all color information. Most OpenCV functions consider information to be written in white, and the background to be black. So, let's start by creating a threshold function to match this criteria:
#include opencv2/opencv.hpp;
#include vector;
using namespace std;
using namespace cv;
Mat binarize(Mat input)
{
//Uses otsu to threshold the input image
Mat binaryImage;
cvtColor(input, input, COLOR_BGR2GRAY);
threshold(input, binaryImage, 0, 255, THRESH_OTSU);
//Count the number of black and...