tesseract.py

# USAGE
# python localize_text_tesseract.py --image apple_support.png
# python localize_text_tesseract.py --image apple_support.png --min-conf 50

# import the necessary packages
from pytesseract import Output
import pytesseract
import argparse
import cv2

# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,help="path to input image to be OCR'd")
ap.add_argument("-c", "--min-conf", type=int, default=0,help="mininum confidence value to filter weak text detection")
args = vars(ap.parse_args())

# load the input image, convert it from BGR to RGB channel ordering,
# and use Tesseract to localize each area of text in the input image
image = cv2.imread(args["image"])
rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
results = pytesseract.image_to_data(rgb, output_type=Output.DICT)

# loop over each of the individual text localizations
for i in range(0, len(results["text"])):
	# extract the bounding box coordinates of the text region from
	# the current result
	x = results["left"][i]
	y = results["top"][i]
	w = results["width"][i]
	h = results["height"][i]

	# extract the OCR text itself along with the confidence of the
	# text localization
	text = results["text"][i]
	conf = int(results["conf"][i])

	# filter out weak confidence text localizations
	if conf > args["min_conf"]:
		# display the confidence and text to our terminal
		print("Confidence: {}".format(conf))
		print("Text: {}".format(text))
		print("")

		# strip out non-ASCII text so we can draw the text on the image
		# using OpenCV, then draw a bounding box around the text along
		# with the text itself
		text = "".join([c if ord(c) < 128 else "" for c in text]).strip()
		cv2.rectangle(image, (x, y), (x + w, y + h), (0, 0, 255), 2)
		#cv2.putText(image, text, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX,1.2, (0, 0, 255), 3)

# show the output image
cv2.imshow("Image", image)
cv2.waitKey(0)

parse_text = []
word_list = []
last_word = ''
for word in results['text']:
    if word!='':
        word_list.append(word)
        last_word = word
    if (last_word!='' and word == '') or (word==results['text'][-1]):
        parse_text.append(word_list)
        word_list = []

import csv
with open("result_text22.txt", 'w', newline="") as file:
     csv.writer(file, delimiter=" ").writerows(parse_text)