How to convert an image into character segments?

Question

Often in the process of OCR, an image file is essentially cut into segments, and each character is recgnised as a segment each. For instance,

has to be transformed to something like

Also, is there any algorithm for Asian languages like Telugu readily available for this purpose? If not, how is this done for English?

Answer 1

It can be easily done using OpenCV. Below is a sample code:

import cv2
import numpy as np

# Load the image
img = cv2.imread('sof.png')

# convert to grayscale
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

# smooth the image to avoid noises
gray = cv2.medianBlur(gray,5)

# Apply adaptive threshold
thresh = cv2.adaptiveThreshold(gray,255,1,1,11,2)
thresh_color = cv2.cvtColor(thresh,cv2.COLOR_GRAY2BGR)

# apply some dilation and erosion to join the gaps
thresh = cv2.dilate(thresh,None,iterations = 3)
thresh = cv2.erode(thresh,None,iterations = 2)

# Find the contours
contours,hierarchy = cv2.findContours(thresh,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)

# For each contour, find the bounding rectangle and draw it
for cnt in contours:
    x,y,w,h = cv2.boundingRect(cnt)
    cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),2)
    cv2.rectangle(thresh_color,(x,y),(x+w,y+h),(0,255,0),2)

# Finally show the image
cv2.imshow('img',img)
cv2.imshow('res',thresh_color)
cv2.waitKey(0)
cv2.destroyAllWindows()

Output will look like below: