def worker(file):
"""thread worker function"""
# time.sleep(0.5)
print '\nWorker' + image
scan_image(file)
get_qr_code(file + "-result.png")
# print image
return
def index():
if request.method == 'POST':
imageFile = request.files['imageFile']
imageFile.save(UPLOADED_FILE)
scanned_image = scan_image(UPLOADED_FILE)
scanned_image.save('scanned_images/scanned_image.png')
return send_file('scanned_images/scanned_image.png')
return render_template('index.html')
def ocr_scan_deal(self): #OCR识别
global image, img2
#cv2.imshow('image',image)
img2 = scan.scan_image(image)
img3 = cv2.cvtColor(img2, cv2.COLOR_GRAY2BGR)
img4 = cv2.resize(img3, (image_height, image_width),
interpolation=cv2.INTER_AREA)
self.label2_image_show(img4)
cv2.imwrite('ocr_scan.jpg', img3)
text = pytesseract.image_to_string(Image.open('ocr_scan.jpg'))
print(text)
self.textEdit.setText(text)
self.pushButton_3.setEnabled(True)
def scan_data(scanarium, data):
with tempfile.TemporaryDirectory(prefix='scanarium-scan-data-') as dir:
image_file = os.path.join(dir, 'image')
with open(image_file, 'wb') as f:
f.write(base64.standard_b64decode(data))
# Temporarily switching the image source to the new image for scanning
scanarium.set_config('scan', 'source', f'image:{image_file}')
# As we switched from the configured image source to the passed image,
# the calibration data for the configured image source no longer fits,
# and we drop it as it may otherwise distort colors/geometry.
scanarium.set_config('scan', 'calibration_xml_file', '')
scanarium.set_config('scan', 'max_brightness', '')
return scan_image(scanarium)
def photo_to_dict(photo):
scanned_text = scan.scan_image(photo)
final_dict = {}
amounts = extract.amounts_extraction(scanned_text) # dict
final_dict.update(amounts)
final_dict['mjesto_izdavanja'] = extract.postal_numbers(
scanned_text) # string
dates = extract.payment_dates(scanned_text) # dict
final_dict.update(dates)
# Na temelju oib-a se iz baze povlace podaci o korisniku i izdavacu racuna
user_data, company_data = extract.oib_numbers(scanned_text)
final_dict.update(user_data)
company_data['iban_primatelja'] = extract.iban_numbers(
scanned_text, company_data)
del company_data['iban']
final_dict.update(company_data)
return final_dict
# compute the new bounding dimensions of the image
nW = int((h * sin) + (w * cos))
nH = int((h * cos) + (w * sin))
# adjust the rotation matrix to take into account translation
M[0, 2] += (nW / 2) - cX
M[1, 2] += (nH / 2) - cY
# perform the actual rotation and return the image
return cv2.warpAffine(image, M, (nW, nH))
if img.shape[1] < img.shape[0]:
res = rotate_bound(img, 90)
else:
res = img
scanned = scan.scan_image(img) #文本内容边框识别，变换处理，若需要则将下面第二行的img改为scanned
#cv_show('scan',scanned)
print(res.shape)
print(img.shape)
cv_show('res', res)
cv_show('img', img)
roi = res[0:int(res.shape[0] * 0.08), int(res.shape[1] * 0.7):res.shape[1]]
#cv_show('roi',roi)
ret, roi_binary = cv2.threshold(roi, 127, 255, cv2.THRESH_BINARY_INV) #翻转二值化处理
cv_show('roi_binary', roi_binary)
number = pytesseract.image_to_string(roi_binary)
print(number)