You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
27 lines
780 B
Python
27 lines
780 B
Python
2 years ago
|
from PIL import Image
|
||
|
|
from pytesseract import pytesseract
|
||
|
|
import os
|
||
|
|
|
||
|
|
#Define path to tessaract.exe #or equivalent on os
|
||
|
|
path_to_tesseract = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
|
||
|
|
|
||
|
|
#Define path to image
|
||
|
|
#path_to_image = 'input/sampletext1-ocr.png'
|
||
|
|
#Define path to images folder
|
||
|
|
path_to_input = r'input/'
|
||
|
|
path_to_output = r'output/'
|
||
|
|
|
||
|
|
#Point tessaract_cmd to tessaract.exe
|
||
|
|
pytesseract.tesseract_cmd = path_to_tesseract
|
||
|
|
|
||
|
|
#Get the file names in the directory
|
||
|
|
for root, dirs, file_names in os.walk(path_to_input):
|
||
|
|
#Iterate over each file name in the folder
|
||
|
|
for file_name in file_names:
|
||
|
|
#Open image with PIL
|
||
|
|
img = Image.open(path_to_input + file_name)
|
||
|
|
|
||
|
|
#Extract text from image
|
||
|
|
text = pytesseract.image_to_string(img)
|
||
|
|
|
||
|
|
print(text)
|