Commit 25c880c6 authored by salecha sravan kumar jain's avatar salecha sravan kumar jain
Browse files

ocr-here we have recognized the contet of an image with various languages

parent 0744dd12
import cv2
import numpy as np
import pytesseract
from PIL import Image
# Path of working folder on Disk
src_path = "/home/sravanjain/Desktop"
import cv2
import numpy as np
import pytesseract
from PIL import Image
# Path of working folder on Disk
src_path = "/home/sravanjain/Desktop/tel.jpeg"
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)
print(result)
print('--- Start recognize text from image ---')
get_string("/home/sravanjain/Desktop/tel.jpeg")
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment