OCR - question pytesseract

Question

J'essaie d'appliquer le code ci-dessous:

import cv2 
import numpy as np 
import pytesseract 
from PIL import Image 

# Path of working folder on Disk 
src_path = "C:/TEST/" 

def get_string(img_path): 
    # Read image with opencv 
    img = cv2.imread(img_path) 

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

    # Apply dilation and erosion to remove some noise 
    kernel = np.ones((1, 1), np.uint8) 
    img = cv2.dilate(img, kernel, iterations=1) 
    img = cv2.erode(img, kernel, iterations=1) 

    # Write image after removed noise 
    cv2.imwrite(src_path + "removed_noise.png", img) 

    # Apply threshold to get image with only black and white 
    #img = cv2.adaptiveThreshold(img, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 31, 2) 

    # Write the image after apply opencv to do some ... 
    cv2.imwrite(src_path + "thres.png", img) 

    # Recognize text with tesseract for python 
    result = pytesseract.image_to_string(Image.open(src_path + "thres.png")) 

    # Remove template file 
    #os.remove(temp) 

    return result 


print '--- Start recognize text from image ---' 
print get_string(src_path + "textArea01.png") 

Mais en retour, je reçois

Traceback (most recent call last): 
    File "C:/Python27/erw.py", line 40, in <module> 
    print get_string(src_path + "textArea01.png") 
    File "C:/Python27/erw.py", line 31, in get_string 
    result = pytesseract.image_to_string(Image.open(src_path + "thres.png")) 
    File "C:\Python27\lib\site-packages\pytesseract\pytesseract.py", line 122, in image_to_string 
    config=config) 
    File "C:\Python27\lib\site-packages\pytesseract\pytesseract.py", line 46, in run_tesseract 
    proc = subprocess.Popen(command, stderr=subprocess.PIPE) 
    File "C:\Python27\lib\subprocess.py", line 390, in __init__ 
    errread, errwrite) 
    File "C:\Python27\lib\subprocess.py", line 640, in _execute_child 
    startupinfo) 

* J'ai essayé d'installer tesseract-ocr

mais il finit pour moi:

Command "c:\python27\python.exe -u -c "import setuptools, tokenize;__file__='c:\ 
\users\\xyz~1\\appdata\\local\\temp\\pip-build-bvk9mm\\tesseract-ocr\\setup.p 
y';f=getattr(tokenize, 'open', open)(__file__);code=f.read().replace('\r\n', '\n 
');f.close();exec(compile(code, __file__, 'exec'))" install --record c:\users\df 
asto~1\appdata\local\temp\pip-vcr3xw-record\install-record.txt --single-version- 
externally-managed --compile" failed with error code 1 in c:\users\xyz~1\appd 
ata\local\temp\pip-build-bvk9mm\tesseract-ocr\ 

#

Quand Im essayant code différent:

from PIL import Image 
from pytesseract import image_to_string 

im = image_to_string(Image.open("c:/Python36/Projekty/textArea01.png")) 
print(im) 

même histoire comme ci-dessus:

Traceback (most recent call last): 
    File "C:\Python36\Projekty\OCR_v1.py", line 6, in <module> 
    im = image_to_string(Image.open("c:/Python36/Projekty/textArea01.png")) 
    File "C:\Python36\lib\site-packages\pytesseract\pytesseract.py", line 122, in image_to_string 
    config=config) 
    File "C:\Python36\lib\site-packages\pytesseract\pytesseract.py", line 46, in run_tesseract 
    proc = subprocess.Popen(command, stderr=subprocess.PIPE) 
    File "C:\Python36\lib\subprocess.py", line 707, in __init__ 
    restore_signals, start_new_session) 
    File "C:\Python36\lib\subprocess.py", line 990, in _execute_child 
    startupinfo) 
FileNotFoundError: [WinError 2] 

La question est - comment sortir des questions ci-dessus | et pourquoi je vois ces questions en 1ère fois

Answer 1

Je ne ai pas eu de problèmes avec l'installation Tesseract mais je Tesseract à effet de levier UB installateur Mannheim:

https://github.com/UB-Mannheim/tesseract/wiki

Vous devez également installer pytesseract:

pip3.6 installer pytesseract

J'utilise le code suivant sans problème:

import numpy as np 
from numpy import * 
from PIL import Image 
from PIL import * 
import pytesseract 
import cv2 


src_path = "C:\\Users\\USERNAME\\Documents\\OCR\\" 


def get_string(img_path): 
    # Read image with opencv 
    img = cv2.imread(img_path) 
    # Convert to gray 
    img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) 
    # Apply dilation and erosion to remove some noise 
    kernel = np.ones((1, 1), np.uint8) 
    img = cv2.dilate(img, kernel, iterations=1) 
    img = cv2.erode(img, kernel, iterations=1) 
    # Write image after removed noise 
    cv2.imwrite(src_path + "removed_noise.png", img) 
    # Apply threshold to get image with only black and white 
    #img = cv2.adaptiveThreshold(img, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 31, 2) 
    # Write the image after apply opencv to do some ... 
    cv2.imwrite(src_path + "thres.png", img) 
    # Recognize text with tesseract for python 

    result = pytesseract.image_to_string(Image.open(src_path + "thres.png")) 

    return result 

def main(): 
    #Output results 
    print ("OCR Output: ") 
    print (get_string(src_path + "test.png")) 

Créez un fichier image avec l'extension .png et assurez-vous de modifier le code pour obtenir le chemin et le nom d'image corrects.

Pour m'assurer que l'OCR fonctionne correctement, je recommande de faire en sorte que le texte (ou le texte dans l'image) corresponde à la taille de la police 16. J'ai eu des problèmes avec la police de taille plus petite étant précis ou ne pas être lu du tout.