How to segment the image using OpenCV python when using otsu binarization

In the following solution you can get words separately for each sentence. After getting word by word this will give output character by character.

This is the full code:

import cv2
import numpy as np
image = cv2.imread("stach.png",0)
cv2.imshow('orig',image)
# image = cv2.resize(image_original,None,fx=4, fy=4, interpolation = cv2.INTER_CUBIC)



#dilation
kernel = np.ones((5,100), np.uint8)
img_dilation = cv2.dilate(image, kernel, iterations=1)
# original_resized = cv2.resize(img_dilation, (0,0), fx=.2, fy=.2)
cv2.imshow('dilated',img_dilation)
cv2.waitKey(0)
#find contours
im2,ctrs, hier = cv2.findContours(img_dilation.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

#sort contours
sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[1])

for i, ctr in enumerate(sorted_ctrs):

    # Get bounding box
    x, y, w, h = cv2.boundingRect(ctr)

    # Getting ROI
    roi = image[y:y+h, x:x+w]

# #   show ROI
    cv2.imshow('segment no:' +str(i),roi)
    cv2.waitKey(0)



    im = cv2.resize(roi,None,fx=4, fy=4, interpolation = cv2.INTER_CUBIC)
    ret_1,thresh_1 = cv2.threshold(im,127,255,cv2.THRESH_BINARY_INV)
    # original_resized = cv2.resize(thresh, (0,0), fx=.2, fy=.2)
    cv2.imshow('Threshold_1',thresh_1)
    cv2.waitKey(0)
    cv2.bitwise_not(thresh_1, thresh_1)
    kernel = np.ones((5, 30), np.uint8)
    words = cv2.dilate(thresh_1, kernel, iterations=1)
    cv2.imshow('words', words)
    cv2.waitKey(0)


    #words=cv2.cvtColor(words, cv2.COLOR_BGR2GRAY);

    #find contours
    im,ctrs_1, hier = cv2.findContours(words, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

    #sort contours
    sorted_ctrs_1 = sorted(ctrs_1, key=lambda ctr: cv2.boundingRect(ctr)[0])

    for j, ctr_1 in enumerate(sorted_ctrs_1):

        # Get bounding box
        x_1, y_1, w_1, h_1 = cv2.boundingRect(ctr_1)

        # Getting ROI
        roi_1 = thresh_1[y_1:y_1+h_1, x_1:x_1+w_1]

        # #   show ROI
        cv2.imshow('Line no: ' + str(i) + " word no : " +str(j),roi_1)
        cv2.waitKey(0)

        #chars = cv2.cvtColor(roi_1, cv2.COLOR_BGR2GRAY);

        # dilation
        kernel = np.ones((10, 1), np.uint8)
        joined = cv2.dilate(roi_1, kernel, iterations=1)
        # original_resized = cv2.resize(img_dilation, (0,0), fx=.2, fy=.2)
        cv2.imshow('joined', joined)
        cv2.waitKey(0)

        # find contours
        im, ctrs_2, hier = cv2.findContours(joined, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

        # sort contours
        sorted_ctrs_2 = sorted(ctrs_2, key=lambda ctr: cv2.boundingRect(ctr)[0])



        for k, ctr_2 in enumerate(sorted_ctrs_2):
            # Get bounding box
            x_2, y_2, w_2, h_2 = cv2.boundingRect(ctr_2)

            # Getting ROI
            roi_2 = roi_1[y_2:y_2 + h_2, x_2:x_2 + w_2]

            # #   show ROI
            cv2.imshow('Line no: ' + str(i) + ' word no : ' + str(j) + ' char no: ' + str(k), roi_2)
            cv2.waitKey(0)

First line segmentation should be done. For that following code is used:

kernel = np.ones((5,100), np.uint8)
img_dilation = cv2.dilate(image, kernel, iterations=1)

a kernel of 5x100 is used to seperate lines in the image.

Result is like follows:

After that contours will be extracted from above image and apply that contour coordinates to the original image. Then lines of the image will be extracted. Example line is as follows:

Then to each of these lines another kernel will be applied to extract words using the same method which applied to extract lines.

kernel = np.ones((5, 30), np.uint8)
words = cv2.dilate(thresh_1, kernel, iterations=1)

After extracting word by word then character by character will be extracted using following code:

for k, ctr_2 in enumerate(sorted_ctrs_2):
    # Get bounding box
    x_2, y_2, w_2, h_2 = cv2.boundingRect(ctr_2)

    # Getting ROI
    roi_2 = roi_1[y_2:y_2 + h_2, x_2:x_2 + w_2]

Hope you understand the method I provided. You can make changes as per your requirement to the full code.