# import the necessary packages from pyimagesearch.alignment import align_images from collections import namedtuple import pytesseract import argparse import imutils import cv2 import numpy as np image = 'Documents/ocr-document/scans/File_000.jpg' template = 'Documents/ocr-document/form_w4.png' image = cv2.imread(image) template = cv2.imread(template) aligned = align_images(image, template, debug=True)
["employee", "signature", "form", "valid", "unless", "you", "sign"]),
OCRLocation("step5_date", (1804, 2516, 504, 156), ["date"]),
OCRLocation("employee_name_address", (265, 2706, 1224, 180),
["employer", "name", "address"]),
OCRLocation("employee_ein", (1831, 2706, 448, 180),
["employer", "identification", "number", "ein"]),
]
# load the input image and template from disk
print("[INFO] loading images...")
image = cv2.imread(args["image"])
template = cv2.imread(args["template"])
# align the images, on the template!!
print("[INFO] aligning images...")
aligned = align_images(image, template)
if args["verbose"] == 'true':
cv2.imshow("Aligned", imutils.resize(aligned, width=700))
# initialize a results list to store the document OCR parsing results
print("[INFO] OCR'ing document...")
parsingResults = []
winNum = 1
# loop over the locations of the document we are going to OCR
for loc in OCR_LOCATIONS:
# extract the OCR ROI from the aligned image
(x, y, w, h) = loc.bbox
roi = aligned[y:y + h, x:x + w]
if args["verbose"] == 'true':
cv2.imshow("ROI#{}".format(winNum), roi)
print('PDF Detected, Converting to .jpg...')
args['image'] = convert_pdf(args['image'])
image = cv2.imread(str(args["image"]))
print(type(image))
template = cv2.imread(args["template"])
# align the images
print("[INFO] aligning images...")
scale = 2
if args['threshold'] == None:
y, x, _ = image.shape
aligned = cv2.resize(image, (scale * 2 * x, scale * 2 * y))
else:
threshold = float(args['threshold'])
aligned = align_images(cv2.threshold(image, 130, 255,
cv2.THRESH_BINARY)[1],
template,
debug=False)
# aligned = align_images(image, template, debug=False)
y, x, _ = aligned.shape
print(f"orignal.shape: {aligned.shape}")
aligned = cv2.resize(aligned, (scale * 2 * x, scale * 2 * y))
# initialize a results list to store the document OCR parsing results
print("[INFO] OCR'ing document...")
parsingResults = []
# loop over the locations of the document we are going to OCR
for loc in OCR_LOCATIONS:
# extract the OCR ROI from the aligned image
(x, y, w, h) = tuple([scale * t for t in loc.bbox])
roi = aligned[y:y + h, x:x + w]