def find_cuts(img):
window = 19
img = cut_letters.removeWhitelines(word_img)
if img is not None:
if len(img[0]) <= window:
cuts = [0, len(img[0])-1]
else:
hist = cut_letters.makeHist(img, window)
cuts = cut_letters.findMaxima(hist)
return cuts
else:
logger.warning('Image not good for classifying')
return None
for f in out_dir.walk('*'):
f.remove()
logger.info('Starting to create a split file')
for sentence in xml:
for word in sentence:
text = word.get('text')
print(text)
#if '@' in text or len(text) < 6:
if text != 'buton':
continue # Skip short words
# Get the word image
rect = {side: int(word.get(side)) for side in sides}
word_img = img[rect['top']:rect['bottom'], rect['left']:rect['right']]
word_img = cut_letters.removeWhitelines(word_img)
if word_img is None:
logger.warning('Word not good for classifying: {}'.format(text))
continue
# Get the cuts
cuts = find_cuts(word_img)
if cuts is None:
logger.warning('No cuts found in word')
continue
cv2.imwrite(out_dir + 'original.png', word_img)
cuts_img = cut_letters.showCuts(word_img.copy(), cuts)
cv2.imwrite(out_dir + 'cuts.png', cuts_img)
i = 0
