Ross
139 lines
4.1 KiB
Python
139 lines
4.1 KiB
Python
|
|
from PIL import Image
|
|
import pytesseract
|
|
import argparse
|
|
import cv2
|
|
import os
|
|
import glob
|
|
|
|
from pathlib import Path
|
|
|
|
|
|
def ocr_file(filename):
|
|
# load the example image and convert it to grayscale
|
|
image = cv2.imread(filename)
|
|
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
|
|
# check to see if we should apply thresholding to preprocess the
|
|
# image
|
|
|
|
text = pytesseract.image_to_string(Image.open(filename))
|
|
|
|
gray_mask = cv2.threshold(gray, 220, 255,
|
|
cv2.THRESH_BINARY)[1]
|
|
|
|
temp_file = "{}.png".format(os.getpid())
|
|
cv2.imwrite(temp_file, gray_mask)
|
|
|
|
# load the image as a PIL/Pillow image, apply OCR, and then delete
|
|
# the temporary file
|
|
text = text + pytesseract.image_to_string(Image.open(temp_file))
|
|
os.remove(temp_file)
|
|
#print(text)
|
|
return text
|
|
|
|
# show the output images
|
|
#cv2.imshow("Image", image)
|
|
#cv2.imshow("Output", gray)
|
|
#cv2.waitKey(0)
|
|
|
|
def check_text(text):
|
|
text = text.lower()
|
|
strings = ("REF", "RK9", "RBZ", "RA9", "RH8", "Accession", "patient", "nhs")
|
|
if any(s.lower() in text for s in strings):
|
|
return True
|
|
|
|
def search_image(file_name):
|
|
print("Process: {}".format(file_name))
|
|
img = cv2.imread(file_name)
|
|
|
|
img_final = cv2.imread(file_name)
|
|
img2gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
|
|
ret, mask = cv2.threshold(img2gray, 240, 255, cv2.THRESH_BINARY)
|
|
|
|
#cv2.imshow("mask", mask)
|
|
|
|
image_final = cv2.bitwise_and(img2gray, img2gray, mask=mask)
|
|
#ret, new_img = cv2.threshold(image_final, 180, 255, cv2.THRESH_BINARY) # for black text , cv.THRESH_BINARY_INV
|
|
'''
|
|
line 8 to 12 : Remove noisy portion
|
|
'''
|
|
kernel = cv2.getStructuringElement(cv2.MORPH_CROSS, (3,
|
|
3)) # to manipulate the orientation of dilution , large x means horizonatally dilating more, large y means vertically dilating more
|
|
dilated = cv2.dilate(image_final, kernel, iterations=9) # dilate , more the iteration more the dilation
|
|
|
|
# for cv2.x.x
|
|
|
|
#_, contours, hierarchy = cv2.findContours(dilated, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE) # findContours returns 3 variables for getting contours
|
|
|
|
# for cv3.x.x comment above line and uncomment line below
|
|
|
|
contours, hierarchy = cv2.findContours(dilated,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)
|
|
|
|
|
|
|
|
for contour in contours:
|
|
# get rectangle bounding contour
|
|
[x, y, w, h] = cv2.boundingRect(contour)
|
|
|
|
# Don't plot small false positives that aren't text
|
|
if w < 35 and h < 35:
|
|
continue
|
|
|
|
|
|
#you can crop image and send to OCR , false detected will return no text :)
|
|
cropped = image_final[y :y + h , x : x + w]
|
|
|
|
s = 'temp.png'
|
|
cv2.imwrite(s , cropped)
|
|
text = ocr_file(s)
|
|
os.remove(s)
|
|
|
|
#cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)
|
|
|
|
if check_text(text):
|
|
# draw rectangle around contour on original image
|
|
cv2.rectangle(img, (x, y), (x + w, y + h), (0, 0, 0), -1)
|
|
|
|
path, fn = file_name.rsplit("/", 1)
|
|
|
|
edit_path = "{}/test/".format(path)
|
|
|
|
Path(edit_path).mkdir(parents=True, exist_ok=True)
|
|
|
|
print(edit_path)
|
|
fn1, fn2 = fn.rsplit(".", 1)
|
|
cv2.imwrite("{}{}_new.{}".format(edit_path, fn1, fn2), img)
|
|
|
|
old_img = cv2.imread(file_name)
|
|
cv2.imwrite("{}{}".format(edit_path, fn), old_img)
|
|
|
|
|
|
# write original image with added contours to disk
|
|
#cv2.imshow('captcha_result', img)
|
|
#cv2.waitKey()
|
|
|
|
|
|
|
|
#file_name = 'ankle4.jpg'
|
|
#captch_ex(file_name)
|
|
#
|
|
#file_name = 'ankle1_n2mBhsm.jpg'
|
|
#captch_ex(file_name)
|
|
#ocr_file("ankle4.jpg")
|
|
|
|
# file_name = 'chest_UUSUv8E.jpg'
|
|
# captch_ex(file_name)
|
|
#file_name = 'l1_DvMrQpv.jpg'
|
|
#captch_ex(file_name)
|
|
#file_name = 'renalmets_ct.jpg'
|
|
#captch_ex(file_name)
|
|
image_list = []
|
|
|
|
file_types = ("gif", "jpg", "jpeg", "png")
|
|
for file_type in file_types:
|
|
for filename in glob.glob('/home/ross/scripts/sites/backups/New/media/rapids/*.{}'.format(file_type)): #assuming gif
|
|
image_list.append(filename)
|
|
|
|
for f in image_list:
|
|
search_image(f)
|