def get_writing_features(image_path):
# Pre-processing
gray_img = cv.imread(image_path, cv.IMREAD_GRAYSCALE)
gray_img, bin_img = PreProcessor.process(gray_img)
gray_lines, bin_lines = LineSegmentor(gray_img, bin_img).segment()
# Feature extraction
return FeatureExtractor(gray_lines, bin_lines).extract()
def get_features(path):
# Read and pre-process the image
gray_img = cv.imread(path, cv.IMREAD_GRAYSCALE)
gray_img, bin_img = PreProcessor.process(gray_img)
gray_lines, bin_lines = LineSegmentor(gray_img, bin_img).segment()
# Extract features of every line separately
x = []
for g, b in zip(gray_lines, bin_lines):
f = FeatureExtractor([g], [b]).extract()
x.append(f)
# Return list of features for every line in the image
return x
def main(args):
feature_extractor = FeatureExtractor(get_resources(), args.model)
train_feats, train_labels, _, _ = feature_extractor.get_features(
args.train, args.train_topk)
test_feats, _, test_segs, test_gold_truths = feature_extractor.get_features(
args.test, args.test_topk)
epochs, lr1, lr2 = 100, 0.01, 0.05
# Initialize model
model = None
if args.model == "mse":
model = mse_ranker.MSERanker(epochs, lr1)
elif args.model == "mr":
model = mr_ranker.MRRanker(epochs, lr1)
elif args.model == "mse_multi":
model = mse_multi_ranker.MSEMultiRanker(epochs, lr1, lr2)
elif args.model == "mr_multi":
model = mr_multi_ranker.MRMultiRanker(epochs, lr1, lr2)
# Train model
model.train(train_feats, train_labels)
# Rerank top-k segmentations
top_segmentations = []
for segs_feats, segs, gds in zip(test_feats, test_segs, test_gold_truths):
if len(segs) == 1:
top_segmentations.extend(segs)
else:
reranked_segs = rerank(segs, segs_feats, model, args.model)
top_segmentations.append(reranked_segs)
if args.output is not None:
fp = open(args.output, 'w')
for segs in top_segmentations:
target = "".join(segs[0].split())
fp.write(target + "\t" + "\t".join([seg.strip()
for seg in segs]) + "\n")
fp.close()
# Evaluate metrics
print("MRR:", mean_reciprocal_rank(test_gold_truths, top_segmentations))
print("Accuracy@1:", accuracy(1, test_gold_truths, top_segmentations))
print("Accuracy@2:", accuracy(2, test_gold_truths, top_segmentations))
print("Fscore@1:", fscore(1, test_gold_truths, top_segmentations))
print("Fscore@2:", fscore(2, test_gold_truths, top_segmentations))
def get_writer_features(path, writer_id):
# All lines of the writer
total_gray_lines, total_bin_lines = [], []
# Read and append all lines of the writer
for root, dirs, files in os.walk(path):
for filename in files:
gray_img = cv.imread(path + filename, cv.IMREAD_GRAYSCALE)
gray_img, bin_img = PreProcessor.process(gray_img)
gray_lines, bin_lines = LineSegmentor(gray_img, bin_img).segment()
total_gray_lines.extend(gray_lines)
total_bin_lines.extend(bin_lines)
break
# Extract features of every line separately
x, y = [], []
for g, b in zip(total_gray_lines, total_bin_lines):
f = FeatureExtractor([g], [b]).extract()
x.append(f)
y.append(writer_id)
return x, y
def extract_features(txt_io, feat_io, cword_io, train=False, factor_files={}):
csets = CSetPair(config['source-cset'], config['target-cset'])
extractor = FeatureExtractor(csets, config['features'], config['costs'])
check_factor_requirements(extractor.required_factors(), factor_files)
finder = CWordFinder(csets, train)
if config['nulls-ngrams']:
null_finder = NullFinder(csets.src, config['nulls-ngrams'])
finder.add_extra_finder(null_finder)
reader = CWordReader(cword_io)
log.info("Extract features from {}".format(txt_io.name))
count = 0
for sid, line, fact_sent in each_factorized_input(txt_io, factor_files):
for cword in finder.find_confusion_words(line, fact_sent):
feat_str = extractor.extract_features(cword, fact_sent)
feat_io.write(feat_str)
reader.format(sid, cword)
count += 1
log.info("Found {} confusion words".format(count))
# Choose statistical features and physical parameters
features_list = [fc.get_min, fc.get_max, fc.get_median]
params_name_list = ['TOTUSJH', 'TOTBSQ', 'TOTPOT', 'TOTUSJZ']
# Input and output path
#path_to_root = os.path.join('..', CONST.IN_PATH_TO_MVTS_FL)
#path_to_dest = os.path.join('..', CONST.OUT_PATH_TO_RAW_FEATURES)
#path_to_root = CONST.IN_PATH_TO_MVTS_FL
path_to_root = CONST.IN_PATH_TO_MVTS_FL2
path_to_dest = CONST.OUT_PATH_TO_RAW_FEATURES
output_filename = 'raw_features_p2_FL.csv'
# Extract features
pc = FeatureExtractor(path_to_root, path_to_dest, output_filename)
pc.calculate_all(features_list, params_name_list=params_name_list)
path_to_root = CONST.IN_PATH_TO_MVTS_NF2
path_to_dest = CONST.OUT_PATH_TO_RAW_FEATURES
output_filename = 'raw_features_p2_NF.csv'
# Extract features
pc = FeatureExtractor(path_to_root, path_to_dest, output_filename)
pc.calculate_all(features_list, params_name_list=params_name_list)
path_to_root = CONST.IN_PATH_TO_MVTS_FL3
path_to_dest = CONST.OUT_PATH_TO_RAW_FEATURES
output_filename = 'raw_features_p3_FL.csv'
# Extract features