def get_qualitative_results_lines(denoise_func):
sclite.clear()
test_ds_line = IAMDataset("line", train=False)
for i in tqdm(range(1, len(test_ds_line))):
image, text = test_ds_line[i]
line_image = exposure.adjust_gamma(image, 1)
line_image = handwriting_recognition_transform(line_image, line_image_size)
character_probabilities = handwriting_line_recognition_net(line_image.as_in_context(ctx))
decoded_text = denoise_func(character_probabilities)
actual_text = text[0].replace(""", '"').replace("'","'").replace("&", "&")
sclite.add_text([decoded_text], [actual_text])
cer, er = sclite.get_cer()
print("Mean CER = {}".format(cer))
return cer
import ocr.utils.denoiser_utils
import ocr.utils.beam_search
importlib.reload(ocr.utils.denoiser_utils)
from ocr.utils.denoiser_utils import SequenceGenerator
importlib.reload(ocr.utils.beam_search)
from ocr.utils.beam_search import ctcBeamSearch
from ocr.paragraph_segmentation_dcnn import SegmentationNetwork, paragraph_segmentation_transform
from ocr.word_and_line_segmentation import SSD as WordSegmentationNet, predict_bounding_boxes
from ocr.handwriting_line_recognition import Network as HandwritingRecognitionNet, handwriting_recognition_transform
from ocr.handwriting_line_recognition import decode as decoder_handwriting, alphabet_encoding
ctx = mx.gpu(0) if mx.context.num_gpus() > 0 else mx.cpu()
test_ds = IAMDataset("form_original", train=False)
test_ds = IAMDataset("form_original", train=False)
figs_to_plot = 4
images = []
random.seed(1)
n = 0
for i in range(0, figs_to_plot):
n = int(random.random() * len(test_ds))
image, _ = test_ds[n]
images.append(image)
fig, axs = plt.subplots(int(len(images) / 2),
2,
figsize=(15, 10 * len(images) / 2))
for i, image in enumerate(images):
0.03, 0.03) if detection_box == "line" else (0.005, 0.005)
random_remove_box = 0.1
log_dir = "./logs/line_word_segmentation"
checkpoint_dir, checkpoint_name = "model_checkpoint", "ssd_" + detection_box + ".params"
print_every_n = 5
send_image_every_n = 20
save_every_n = 50
#%%
#############################################################
ctx = [mx.cpu(i) for i in range(cpu_count)]
##############################################################
train_ds = IAMDataset("form_bb",
output_data="bb",
output_parse_method=detection_box,
train=True)
print("Number of training samples: {}".format(len(train_ds)))
test_ds = IAMDataset("form_bb",
output_data="bb",
output_parse_method=detection_box,
train=False)
print("Number of testing samples: {}".format(len(test_ds)))
train_data = gluon.data.DataLoader(train_ds.transform(augment_transform),
batch_size,
shuffle=True,
last_batch="rollover",
num_workers=8)
test_data = gluon.data.DataLoader(test_ds.transform(transform),
from ocr.utils.iam_dataset import IAMDataset
# # Paragraph Segmentation
# This notebook investigates methods to identify segment passages from images that contains printed and handwritten text using the **MSER algorithm**.
#
# *Input*: a png from the IAM dataset with the "form" input and output type of "bb" and form.
#
# *Output*: a bounding boxes of the paragraphs.
#
# ## Dataset creation
# In[3]:
train_ds = IAMDataset("form",
output_data="bb",
output_parse_method="form",
train=True)
print("Number of training samples: {}".format(len(train_ds)))
test_ds = IAMDataset("form",
output_data="bb",
output_parse_method="form",
train=False)
print("Number of testing samples: {}".format(len(test_ds)))
# ## MSER based text region detection
#
# The MSER algorithm has been used in text regions detection [1]. Although this was mainly applied to printed text, we tested this technique to segment documents with both handwritten and printed text.
# ### Detecting text region proposals
num_downsamples = 2
resnet_layer_id = 4
lstm_hidden_states = 512
lstm_layers = 2
random_y_translation, random_x_translation = 0.03, 0.03
random_y_scaling, random_x_scaling = 0.1, 0.1
random_shearing = 0.7
log_dir = "./logs/handwriting_recognition"
checkpoint_dir = "model_checkpoint"
checkpoint_name = "handwriting.params"
# In[18]:
train_ds = IAMDataset("line", output_data="text", train=True)
print("Number of training samples: {}".format(len(train_ds)))
test_ds = IAMDataset("line", output_data="text", train=False)
print("Number of testing samples: {}".format(len(test_ds)))
# In[ ]:
train_data = gluon.data.DataLoader(train_ds.transform(augment_transform),
batch_size,
shuffle=True,
last_batch="rollover",
num_workers=4)
test_data = gluon.data.DataLoader(
test_ds.transform(transform),
batch_size,
resnet_layer_id = 4
lstm_hidden_states = 512
lstm_layers = 2
random_y_translation, random_x_translation = 0.03, 0.03
random_y_scaling, random_x_scaling = 0.1, 0.1
random_shearing = 0.7
log_dir = "./logs/handwriting_recognition"
checkpoint_dir = "model_checkpoint"
checkpoint_name = "handwriting.params"
#%%
train_ds = IAMDataset("line", output_data="text", train=True)
print("Number of training samples: {}".format(len(train_ds)))
test_ds = IAMDataset("line", output_data="text", train=False)
print("Number of testing samples: {}".format(len(test_ds)))
#%%
train_data = gluon.data.DataLoader(train_ds.transform(augment_transform), batch_size, shuffle=True, last_batch="rollover", num_workers=4)
test_data = gluon.data.DataLoader(test_ds.transform(transform), batch_size, shuffle=True, last_batch="keep", num_workers=4)#, num_workers=multiprocessing.cpu_count()-2)
#%%
net = CNNBiLSTM(num_downsamples=num_downsamples, resnet_layer_id=resnet_layer_id , rnn_hidden_states=lstm_hidden_states, rnn_layers=lstm_layers, max_seq_len=max_seq_len, ctx=ctx)
net.hybridize()
ctx = mx.cpu(0) #if mx.context.num_gpus() > 0 else mx.cpu()
# ## Dataset creation
# Obtain the original forms from the IAM dataset and plot the results. Randomly select 4 images for analysis.
# In[3]:
im11 = np.asarray(cv2.imread('test6.png', cv2.IMREAD_GRAYSCALE))
im12 = np.asarray(cv2.imread('test2.png', cv2.IMREAD_GRAYSCALE))
im13 = np.asarray(cv2.imread('test3.png', cv2.IMREAD_GRAYSCALE))
im14 = np.asarray(cv2.imread('test4.png', cv2.IMREAD_GRAYSCALE))
im15 = np.asarray(cv2.imread('test5.png', cv2.IMREAD_GRAYSCALE))
test_ds = IAMDataset("form_original",credentials=("sapand","saurabh12345"), train=False)
# In[4]:
random.seed(1)
# In[5]:
figs_to_plot = 4
images = []
n = 0