├── licence.jpg
├── licence_R.png
├── README.md
└── OCR_Algo.py


/licence.jpg:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Spidy20/Optical_Character_Reccognition/HEAD/licence.jpg


--------------------------------------------------------------------------------
/licence_R.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Spidy20/Optical_Character_Reccognition/HEAD/licence_R.png


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | ##  Optical Character Recognition
 2 | 
 3 | ## NOTE:- I downloaded this image from Google,if you have any query or problem i can remove it, i just used it for Educational purpose.
 4 | 
 5 | ### Code Requirements
 6 | - Pytesseract
 7 | - OCR should be install on your system
 8 | 
 9 | ### What steps you have to follow??
10 | - Download my repository 
11 | - Run `OCR_Algo.py` and see the result.
12 | - Try with your own images.
13 | 
14 | ### How it works? See:)
15 | 
16 | ### Orignal image
17 | 
18 | <img src="https://github.com/Spidy20/Optical_Character_Reccognition/blob/master/licence.jpg">
19 | 
20 | 
21 | ### Output
22 | - it's screenshot of result
23 | - it's in string format, you can do anything with this information.
24 | 
25 | <img src="https://github.com/Spidy20/Optical_Character_Reccognition/blob/master/licence_R.png">\
26 | 
27 | 
28 | ## Just follow☝️ me and Star⭐ my repository 
29 | ## BUY This project which is implemented in WebApp using Flask(FULL WORKING) 
30 | ## HERE is [STORE](https://www.instamojo.com/kushalbhavsar1820/ocr-webapp-using-flask-python)
31 | 


--------------------------------------------------------------------------------
/OCR_Algo.py:
--------------------------------------------------------------------------------
 1 | import pytesseract  ####reading string from image (OCR library)
 2 | import  numpy as np ##numpy for shape
 3 | import cv2   #Computer vision library
 4 | import os    ##for remove image file which we edit during procedure
 5 | pytesseract.pytesseract.tesseract_cmd='C:\\Program Files (x86)\\Tesseract-OCR\\tesseract.exe'
 6 | ###you need to install ocr and give path in program
 7 | try:
 8 |     image='licence.jpg'
 9 |     print('Editing image for better OCR result..........')
10 |     img = cv2.imread(image)  ###reading image
11 |     img = cv2.resize(img, None, fx=1.5, fy=1.5, interpolation=cv2.INTER_CUBIC)
12 |     kernel = np.ones((1, 1), np.uint8)
13 |     img = cv2.dilate(img, kernel, iterations=1)
14 |     img = cv2.erode(img, kernel, iterations=1)
15 |     new_image = 'edited' + '_' + image  ###new image which we save during procedure
16 |     cv2.imwrite(new_image, img)  ###Save a new edited image
17 |     read = pytesseract.image_to_string(new_image)  ####reading from new generated image
18 |     print(read)  ##print resuult
19 | 
20 | except Exception as e:
21 |     print('please provide proper name of the image')
22 |     print(e)
23 | 


--------------------------------------------------------------------------------