text extraction from image using ocr python
1| # importing modules
2| import cv2
3| import pytesseract
5| # reading image using opencv
6| image = cv2.imread(sample_image.png’)
7| #converting image into gray scale image
8| gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
9| # converting it to binary image by Thresholding
10| # this step is require if you have colored image because if you skip this part
11| # then tesseract won't able to detect text correctly and this will give incorrect result
11|threshold_img = cv2.threshold(gray_image, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
12| # display image
13| cv2.imshow(‘threshold image’, threshold_img)
14| # Maintain output window until user presses a key
15| cv2.waitKey(0)
16| # Destroying present windows on screen
17| cv2.destroyAllWindows()