def main():
image = Image.open(sys.argv[1]).convert("L")
num_separator = DigitSeparator(image)
for i,digit in enumerate(num_separator.get_digits()):
img_name = '%s-%d.jpg' % (os.path.basename(sys.argv[1]), i)
with open(os.path.join(sys.argv[2],img_name), 'w') as f:
digit.image.save(f, 'JPEG')
def fit(self, x, y):
digits = []
labels = []
for image, param_labels in zip(x, y):
separator = DigitSeparator(image)
digits.extend(map(self.feature_extractor, separator.get_digits()))
labels.extend(param_labels)
self.vectorizer = DictVectorizer()
train_array = self.vectorizer.fit_transform(digits).toarray()
self.engine.fit(train_array, labels)
def fit(self, x, y):
digits = []
labels = []
for image,param_labels in zip(x,y):
separator = DigitSeparator(image)
digits.extend(map(self.feature_extractor, separator.get_digits()))
labels.extend(param_labels)
self.vectorizer = DictVectorizer()
train_array = self.vectorizer.fit_transform(digits).toarray()
self.engine.fit(train_array, labels)
def __make_prediction(self, image):
separator = DigitSeparator(image)
features = map(self.feature_extractor, separator.get_digits())
digits = self.vectorizer.transform(features).toarray()
labels = self.engine.predict(digits)
return ''.join(map(lambda x: '%d' % x, labels))
def __make_prediction(self, image):
separator = DigitSeparator(image)
features = map(self.feature_extractor, separator.get_digits())
digits = self.vectorizer.transform(features).toarray()
labels = self.engine.predict(digits)
return ''.join(map(lambda x: '%d'%x, labels))