def test_textgrounder(self):
grounder = TextGrounder()
characters = "0" * len(self.segments)
grounder.ground(self.img, self.segments, characters)
self.assertTrue(self.img.is_grounded())
self.assertEquals(reconstruct_chars(self.img.ground.classes),
characters)
def _test_ocr(self, train_file, test_file):
# get data from images
ground_truth = test_file.ground.classes
test_file.remove_ground()
# create OCR
segmenter = ContourSegmenter(blur_y=5, blur_x=5)
extractor = SimpleFeatureExtractor()
classifier = KNNClassifier()
ocr = OCR(segmenter, extractor, classifier)
# train and test
ocr.train(train_file)
chars, classes, _ = ocr.ocr(test_file, show_steps=False)
print chars
print reconstruct_chars(ground_truth)
self.assertEqual(chars, reconstruct_chars(ground_truth))
self.assertEqual(list(classes), list(ground_truth))
def test_terminal_grounder(self):
terminal = TerminalGrounder()
characters = "0" * len(self.segments)
mock_input_gen = iter(characters)
def mock_input(prompt):
return next(mock_input_gen)
with mock.patch('__builtin__.raw_input', mock_input):
terminal.ground(self.img, self.segments)
self.assertTrue(self.img.is_grounded())
self.assertEquals(reconstruct_chars(self.img.ground.classes),
"0" * len(self.segments))
def test_usergrounder(self):
ESC_KEY = 27
ZERO_KEY = 48
keys = [ZERO_KEY] * len(self.segments) + [ESC_KEY]
mock_generator = iter(keys)
def mock_input(*args):
return next(mock_generator)
grounder = UserGrounder()
with mock.patch('cv2.waitKey', mock_input):
with mock.patch('cv2.imshow'):
grounder.ground(self.img, self.segments)
self.assertTrue(self.img.is_grounded)
self.assertEqual(reconstruct_chars(self.img.ground.classes), "0" * len(self.segments))
def test_ocr_digits(self):
# get data from images
img1 = ImageFile('digits1')
img2 = ImageFile('digits2')
ground_truth = img2.ground.classes
img2.remove_ground()
# create OCR
segmenter = ContourSegmenter()
extractor = SimpleFeatureExtractor()
classifier = KNNClassifier()
ocr = OCR(segmenter, extractor, classifier)
# train and test
ocr.train(img1)
chars, classes, _ = ocr.ocr(img2, show_steps=False)
self.assertEqual(list(classes), list(ground_truth))
self.assertEqual(chars, reconstruct_chars(ground_truth))
from feature_extraction import SimpleFeatureExtractor
from classification import KNNClassifier
from ocr import OCR, accuracy, show_differences, reconstruct_chars
segmenter= ContourSegmenter( blur_y=5, blur_x=5, block_size=11, c=10)
extractor= SimpleFeatureExtractor( feature_size=10, stretch=False )
classifier= KNNClassifier()
ocr= OCR( segmenter, extractor, classifier )
ocr.train( ImageFile('digits1') )
test_image= ImageFile('digits2')
test_classes, test_segments= ocr.ocr( test_image, show_steps=True )
print "accuracy:", accuracy( test_image.ground.classes, test_classes )
print "OCRed text:\n", reconstruct_chars( test_classes )
show_differences( test_image.image, test_segments, test_image.ground.classes, test_classes)
########NEW FILE########
__FILENAME__ = feature_extraction
import numpy
import cv2
from segmentation import region_from_segment
from opencv_utils import background_color
FEATURE_DATATYPE= numpy.float32
#FEATURE_SIZE is defined on the specific feature extractor instance
FEATURE_DIRECTION= 1 #horizontal - a COLUMN feature vector
FEATURES_DIRECTION= 0 # vertical - ROWS of feature vectors
class FeatureExtractor( object ):
from files import ImageFile
from segmentation import ContourSegmenter, draw_segments
from feature_extraction import SimpleFeatureExtractor
from classification import KNNClassifier
from ocr import OCR, accuracy, show_differences, reconstruct_chars
segmenter = ContourSegmenter(blur_y=5, blur_x=5, block_size=11, c=10)
extractor = SimpleFeatureExtractor(feature_size=10, stretch=False)
classifier = KNNClassifier()
ocr = OCR(segmenter, extractor, classifier)
ocr.train(ImageFile('digits1'))
test_image = ImageFile('digits2')
test_classes, test_segments = ocr.ocr(test_image, show_steps=True)
print "accuracy:", accuracy(test_image.ground.classes, test_classes)
print "OCRed text:\n", reconstruct_chars(test_classes)
show_differences(test_image.image, test_segments, test_image.ground.classes, test_classes)
