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))
__FILENAME__ = example
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)
########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
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)
if use_tesseract:
api = tesseract.TessBaseAPI()
api.Init(tesslangpath, "eng", tesseract.OEM_DEFAULT)
api.SetPageSegMode(tesseract.PSM_SINGLE_CHAR)
api.SetVariable("classify_enable_learning", "0")
api.SetVariable("classify_enable_adaptive_matcher", "0")
image_dict = OrderedDict()
segment_text_list = []
cluster_pattern_list = []
# classify
for fname in test_images:
test_image = ImageFile(fname)
test_classes, test_segments = ocr.ocr(test_image, show_steps=verbose)
if use_tesseract:
tesseract_image = tesseract.pixRead(fname)
tesseract_classes = []
cluster_list = []
for segment in test_segments:
cluster_segments = prim.get_cluster(segment, test_segments)
if len(cluster_segments) == 10:
add = True
for list_cluster in cluster_list:
add = add and not tesseract_utils.is_cluster_match(
cluster_segments, list_cluster)
if not add:
break
if add:
cluster_list.append(cluster_segments)
if use_tesseract:
api = tesseract.TessBaseAPI()
api.Init(tesslangpath, "eng", tesseract.OEM_DEFAULT)
api.SetPageSegMode(tesseract.PSM_SINGLE_CHAR)
api.SetVariable("classify_enable_learning", "0")
api.SetVariable("classify_enable_adaptive_matcher", "0")
image_dict = OrderedDict()
segment_text_list = []
cluster_pattern_list = []
# classify
for fname in test_images:
test_image = ImageFile(fname)
test_classes, test_segments = ocr.ocr(test_image, show_steps=verbose)
if use_tesseract:
tesseract_image = tesseract.pixRead(fname)
tesseract_classes = []
cluster_list = []
for segment in test_segments:
cluster_segments = prim.get_cluster(segment, test_segments)
if len(cluster_segments) == 10:
add = True
for list_cluster in cluster_list:
add = add and not tesseract_utils.is_cluster_match(cluster_segments, list_cluster)
if not add:
break
if add:
cluster_list.append(cluster_segments)
pattern = tesseract_utils.get_pattern(cluster_segments)
# Assume all current candidates are equally likely
s = sum(c[i - 1] for c in self.candidates)
n = len(self.candidates)
return int(round(float(s) / n))
def __self__(self):
return "<DeckReconstructor, n=%d, avgdeck={1:%d, 2:%d, 3:%d}>" % (len(
self.candidates), self[1], self[2], self[3])
def __repr__(self):
return "<DeckReconstructor, candidates=%s>" % self.candidates
if __name__ == '__main__':
# simple test sequence
import sys, os
dirname, startfn = sys.argv[1:]
deck = None
from ocr import OCR
ocr = OCR("LGE Nexus 5")
imglist = sorted([fn for fn in os.listdir(dirname) if fn >= startfn])
for fn in imglist:
print(fn)
board, tileset = ocr.ocr(os.path.join(dirname, fn))
if deck is None:
deck = DeckReconstructor(board)
deck.update(tileset[0])
print(deck)
elif len(self.candidates) == 1:
return self.candidates[0][i-1]
# Assume all current candidates are equally likely
s = sum(c[i-1] for c in self.candidates)
n = len(self.candidates)
return int(round(float(s)/n))
def __self__(self):
return "<DeckReconstructor, n=%d, avgdeck={1:%d, 2:%d, 3:%d}>" % (len(self.candidates), self[1], self[2], self[3])
def __repr__(self):
return "<DeckReconstructor, candidates=%s>" % self.candidates
if __name__ == '__main__':
# simple test sequence
import sys, os
dirname, startfn = sys.argv[1:]
deck = None
from ocr import OCR
ocr = OCR("LGE Nexus 5")
imglist = sorted([fn for fn in os.listdir(dirname) if fn >= startfn])
for fn in imglist:
print fn
board, tileset = ocr.ocr(os.path.join(dirname, fn))
if deck is None:
deck = DeckReconstructor(board)
deck.update(tileset[0])
print deck
