How to process a binary image to align sparse letters in a row?

Question

I am trying to use tesseract ocr to convert an image to text. The image always have three letters without rotation/skew, but randomly distributed in an 90x50 png file.

By just cleaning and converting to black/white, tesseract could not get the text in the image. After aligning them by hand in Paint, the ocr gives the exact match. I doesn't even need to be exactly aligned. What I want is some tips on how to automate this alignment of the characters in the image prior to sending it to tesseract.

I am using python with tesseract and opencv.

Original image:

What I have done - turn black and white:

What I want to do - aligned by code:

Answer 1

You can use the following code to achieve this output. Some of the constants may need to be changed to fit your needs:

import cv2
import numpy as np

# Read the image (resize so it is easier to see)
img = cv2.imread("/home/stephen/Desktop/letters.png",0)
h,w = img.shape
img = cv2.resize(img, (w*5,h*5))
# Threshold the image and find the contours
_, thresh = cv2.threshold(img, 123, 255, cv2.THRESH_BINARY_INV);
contours, hierarchy = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)

# Create a white background iamge to paste the letters on
bg = np.zeros((200,200), np.uint8)
bg[:] = 255
left = 5

# Iterate through the contours
for contour,h in zip(contours, hierarchy[0]):
    # Ignore inside parts (circle in a 'p' or 'b')
    if h[3] == -1:
        # Get the bounding rectangle
        x,y,w,h = cv2.boundingRect(contour)
        # Paste it onto the background
        bg[5:5+h,left:left+w] = img[y:y+h,x:x+w]
        left += (w + 5)
cv2.imshow('thresh', bg)
cv2.waitKey()