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))
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))
from files import ImageFile
from segmentation import ContourSegmenter
from feature_extraction import SimpleFeatureExtractor
from classification import KNNClassifier
from ocr import OCR, accuracy, show_differences
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_chars, test_classes, test_segments = ocr.ocr(test_image, show_steps=True)
print("accuracy:", accuracy(test_image.ground.classes, test_classes))
print("OCRed text:\n", test_chars)
def setUp(self):
self.img = ImageFile('digits1')
self.img.remove_ground()
self.assertFalse(self.img.is_grounded())
self.segments = ContourSegmenter().process(self.img.image)
boxfile = 'data/' + imgfile + '.box'
new_image = ImageFile(imgfile)
# delete the box file if it's empty
if (isfile(boxfile)):
if (getsize(boxfile) == 0):
remove(boxfile)
# define what to focus on and ignore in the image
stack = [
segmentation_filters.LargeFilter(),
segmentation_filters.SmallFilter(),
segmentation_filters.LargeAreaFilter(),
segmentation_filters.ContainedFilter()
]
# process image, defining useful-looking segments
segmenter = ContourSegmenter(blur_y=5,
blur_x=5,
block_size=11,
c=10,
filters=stack)
segments = segmenter.process(new_image.image)
# uncomment to watch the segmenter in action
#segmenter.display()
grounder = UserGrounder()
grounder.ground(new_image, segments)
new_image.ground.write()
def best_segmenter(image):
'''returns a segmenter instance which segments the given image well'''
return ContourSegmenter()
block_size=17,
c=6,
max_ratio=4.0)
extractor = SimpleFeatureExtractor(feature_size=10, stretch=False)
classifier = KNNClassifier(k=3)
ocr = OCR(segmenter, extractor, classifier)
for file_to_train in args.trainfile:
training_image = ImageFile(file_to_train)
if not training_image.isGrounded() or force_train:
#trainingsegmenter = ContourSegmenter(blur_y=1, blur_x=1, min_width=3, min_height=15, max_height=50, min_area=30, block_size=23, c=3) # tweaked for black font
trainingsegmenter = ContourSegmenter(
blur_y=1,
blur_x=1,
min_width=3,
min_height=15,
max_height=50,
min_area=30,
block_size=3,
c=5,
nearline_tolerance=10.0) # tweaked for white font
segments = trainingsegmenter.process(training_image.image)
if verbose:
trainingsegmenter.display()
# grounder = UserGrounder() # interactive version; lets the user review, assign ground truth data
grounder = TextGrounder(
) # non-interactive ground-truth - assumes clean, ordered input
grounder.ground(training_image, segments,
"0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ"
) # writes out a .box file of image ground truths
verbose = args.verbose
terse = args.terse
force_train = args.retrain
use_tesseract = args.tesseract
tesslangpath = args.tesslangpath
segmenter = MinContourSegmenter(blur_y=5, blur_x=5, min_width=5, block_size=17, c=6, max_ratio=4.0)
extractor = SimpleFeatureExtractor(feature_size=10, stretch=False)
classifier = KNNClassifier(k=3 )
ocr = OCR(segmenter, extractor, classifier)
for file_to_train in args.trainfile:
training_image = ImageFile(file_to_train)
if not training_image.isGrounded() or force_train:
#trainingsegmenter = ContourSegmenter(blur_y=1, blur_x=1, min_width=3, min_height=15, max_height=50, min_area=30, block_size=23, c=3) # tweaked for black font
trainingsegmenter = ContourSegmenter(blur_y=1, blur_x=1, min_width=3, min_height=15, max_height=50, min_area=30, block_size=3 , c=5, nearline_tolerance=10.0 ) # tweaked for white font
segments = trainingsegmenter.process(training_image.image)
if verbose:
trainingsegmenter.display()
# grounder = UserGrounder() # interactive version; lets the user review, assign ground truth data
grounder = TextGrounder() # non-interactive ground-truth - assumes clean, ordered input
grounder.ground(training_image, segments, "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ") # writes out a .box file of image ground truths
ocr.train(training_image)
# Classify given image(s) using training data
test_images = []
dummy_name = args.dir + "\\dummy.jpg"
if os.path.isfile(dummy_name):
from files import ImageFile
from grounding import UserGrounder
from segmentation import ContourSegmenter, draw_segments
segmenter= ContourSegmenter( blur_y=5, blur_x=5, block_size=11, c=10)
new_image= ImageFile('digits1')
segments= segmenter.process(new_image.image)
grounder= UserGrounder()
grounder.ground(new_image, segments);
new_image.ground.write()
