8

I have bounding box(coordinate of rectangle) in an image and want to extract text within that coordinates. How can I use pytesseract to extract text within that coordinates?

I tried copying the image portion to other numpyarray using opencv like 

cropped_image = image[y1:y2][x1:x2]

and tried pytesseract.image_to_string(). But the accuracy was very poor. But when I tried original image to pytesseract.image_to_string() it extracted every thing perfectly..

Is there any function to extract specific portion of image using pytesseract?

This image has different sections of information consider I have rectangle coordinates enclosing 'Online food delivering system' how to extract that data in pytessaract?

Please help Thanks in advance

Versions I am using: Tesseract 4.0.0 pytesseract 0.3.0 OpenCv 3.4.3

nathancy
  • 42,661
  • 14
  • 115
  • 137
Prem Kumar P
  • 93
  • 1
  • 1
  • 6

1 Answers1

9

There's no built in function to extract a specific portion of an image using Pytesseract but we can use OpenCV to extract the ROI bounding box then throw this ROI into Pytesseract. We convert the image to grayscale then threshold to obtain a binary image. Assuming you have the desired ROI coordinates, we use Numpy slicing to extract the desired ROI

enter image description here

From here we throw it into Pytesseract to get our result

ONLINE FOOD DELIVERY SYSTEM

Code

import cv2
import pytesseract

pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"

image = cv2.imread('1.jpg', 0)
thresh = 255 - cv2.threshold(image, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]

x,y,w,h = 37, 625, 309, 28  
ROI = thresh[y:y+h,x:x+w]
data = pytesseract.image_to_string(ROI, lang='eng',config='--psm 6')
print(data)

cv2.imshow('thresh', thresh)
cv2.imshow('ROI', ROI)
cv2.waitKey()
nathancy
  • 42,661
  • 14
  • 115
  • 137