def __init__(self, img):
self.img = img
self.binary_img = binary(img, invert=True)
knn_test = KNNTest(data_path)
self.char_test = Combiner([cont_test, mask_test, knn_test.test]).test
self.objs = [
ImgObj(x, self) for x in connected_components(self.binary_img) if self.good_component(x)
]
self.compute_char_scores()
self.group_words(score_threshold=0.2)
self.spell_corrector = SpellingCorrector('/usr/share/dict/words')
def generate_noise_points(self, output, num_samples):
num_noise_points = 0
for noise_img in self.noise_images:
mat = cv.LoadImageM(noise_img, cv.CV_LOAD_IMAGE_GRAYSCALE)
mat = binary(mat, invert=True)
for com in connected_components(mat):
if 10 < com.mask.rows and 5 < com.mask.cols:
num_noise_points += 1
output.write("\t%s\n" % float_list_to_tsv(params_from_component(com)))
if num_samples <= num_noise_points:
return num_samples
return num_noise_points
