def writeWords( self, name, words, filename ):
os.makedirs( name )
os.chdir( name )
output_file = { 'author': filename.split('-')[0], 'word_count':0, 'words': [], 'features': [] }
word_count = 0
for line in words:
for word in line:
image = word[ 'image' ]
if( np.shape( image )[1] > 0 and np.shape( image )[0] > 0 ):
if( np.shape( word[ 'image' ] )[ 1 ] < self.env.settings.content[ 'extract' ][ 'width'] ):
image = self.buff( image )
output_filename = '{0}_{1}.tif'.format( filename, word_count )
try:
cv2.imwrite( output_filename, image )
except:
error( f'Could not write {output_filename} to a file.' )
output_file[ 'words' ].append( '{0}_{1}.tif'.format( filename, word_count ) )
word_count += 1
output_file[ 'word_count' ] = word_count
open( '{0}.json'.format( filename ), 'a' ).write( json.dumps( output_file, indent=4, sort_keys = True ) )
os.chdir( '..' )
return
def __init__( self, image_path, env ):
state( 'Opening image...' )
self.env = env
if( self.setImage( image_path ) ):
comment( '- Image opened successfully.')
else:
error( 'Could not set image from path in ProcessImage.' )
def getMetric(self, image):
try:
rows, cols = np.shape(image)
open_image = image_utils.Threshold(image, self.env.settings.content['signature']['threshold'])
if open_image.success == False:
return
image = open_image.payload
signature_out = ''
for cols_counter in range(cols):
signature_total = 0
for row_counter in range(rows):
signature_total += image[row_counter][cols_counter]
signature_total = 255 - int(round(signature_total / rows))
signature_out += f'{signature_total}'
return signature_out
except Exception as e:
error(e)
def showImage(image: object):
try:
cv2.imshow('Showing image', image)
cv2.waitKey(0)
return TestMessage(True, 'Image shown successfully.')
except Exception as e:
error(e)
return TestMessage(False, e)
def getJson(self, path: str):
try:
for file in os.listdir(path):
if file.endswith('.json'):
path_to_file = f'{path}/{file}'
return path_to_file
except:
error(f"Could not find a .json file in {path}")
def writeLines( self, name, lines, filename ):
os.makedirs( name )
os.chdir( name )
count = 1
output_file = { 'author': filename.split('-')[0], 'line_count':0, 'lines': [], 'features': [] }
for line in lines:
output_file[ 'lines' ].append( '{0}_{1}.tif'.format( filename, count ) )
try:
cv2.imwrite( '{0}_{1}.tif'.format( filename, count ), line[ 'image' ])
count += 1
except:
error( f'Could not write line to {filename}_{count}.tif')
output_file[ 'line_count' ] = count-1
open( '{0}.json'.format( filename ), 'a' ).write( json.dumps( output_file, indent = 4, sort_keys = True ) )
os.chdir( '..' )
def test_error(self):
"""
Test whether a successful error message can be made to the console.
"""
self.assertEqual(
error('Testing a error message').success, True,
'A successful error message should return a success status of True.'
)
def writeFiles( self, bundle ):
try:
os.makedirs( bundle.getPath() )
os.chdir( bundle.getPath() )
files = Files( bundle.getPath() , self.env )
comment( '- Writing content for subdirectories.' )
files.writeWords( 'words', bundle.words, bundle.folder_name )
files.writeLines( 'lines', bundle.lines, bundle.folder_name )
except:
error( 'Directory already exists.' )
rm_file = input( 'Do you want to remove the directory [Y/n]?' )
if( rm_file.upper() == 'Y' or rm_file == '' ):
os.system( f'rm { bundle.getPath() } -r')
os.makedirs( bundle.getPath() )
os.chdir( bundle.getPath() )
files = Files( bundle.getPath(), self.env )
comment( '- Writing content for subdirectories.' )
files.writeWords( 'words', bundle.words, bundle.folder_name )
files.writeLines( 'lines', bundle.lines, bundle.folder_name )
def __init__(self, env, feature: str, path=None):
state('Setting up the image pipeline.')
self._e = env
if (path != None):
directories = self.getDirectories(path)
if (directories.success):
# Inside each sample folder there are images for lines and words, which are folders.
self.subject = ask('Would you like to use [words] or [lines]?',
readInput.readline())
while (not (self.subject.payload == 'words'
or self.subject.payload == 'lines')):
self.subject = ask('Type either [words] or [lines]?',
readInput.readline())
tmp_create_paths = self.setPaths(self.subject.payload)
if (tmp_create_paths.success):
comment(tmp_create_paths.payload)
feature_files = self.getFeatureFiles()
available_features = self.getListOfAvailableFeatures()
comment('Adding features.')
for feature_class in available_features:
self.save(
self.generateFeatures(feature_files,
feature_class),
feature_class)
else:
error(tmp_create_paths.payload)
raise IOError(tmp_create_paths.payload)
else:
error(directories.payload)
def __init__( self, env, directory, dataset ):
self.env = env
try:
self.processImages( f'{directory}{dataset}/', 'tif' )
except:
error( 'Could not process selected dataset.' )
import os
import cv2
import numpy as np
from PIL import Image
out.state('Running the main application.')
e = Environment(out, os.getcwd())
if (out.confirm('Extract words from images').success):
dataset = out.ask('What dataset would you like to use?')
if (dataset.success):
try:
for key in e.paths.content.keys():
if (key == dataset.payload):
ImagePipeline(e, f'{os.getcwd()}/images/', dataset.payload)
except:
out.error('Extracting failed')
if (out.confirm('Would you like to add a feature?').success):
dataset = out.ask('What dataset would you like to use?')
if (dataset.success):
try:
for key in e.paths.content.keys():
if (key == dataset.payload):
features_pipe = FeaturePipeline(
e, f'{os.getcwd()}/images/{ dataset.payload }')
feature_files = features_pipe.getFeatureFiles()
except:
out.error('Failed to add feature to the dataset.')
