def get_ocr_transformations(image):
filepath = utils.get_filepath(app.config['INPUT_FOLDER'], image)
if filepath is None:
return redirect(url_for('index'))
text = request.form.get('text', '')
transformations = utils.get_images(app.config['OUTPUT_FOLDER'])
results = []
for transformation in transformations:
result_text, percentage = ocr.compare(text, utils.get_filepath(app.config['OUTPUT_FOLDER'], transformation[1]))
results.append({'transformation': transformation[1].split('-')[0], 'original': text, 'result': result_text, 'percentage': percentage})
results = sorted(results, key=itemgetter('percentage'), reverse=True)
result_text, percentage = ocr.compare(text, filepath)
results.insert(0, {'transformation': 'original', 'original': text, 'result': result_text, 'percentage': percentage})
return jsonify(results)
def get_ocr_steps(original, folder):
filepath = utils.get_filepath(app.config['INPUT_FOLDER'], original)
if filepath is None:
return redirect(url_for('index'))
text = request.form.get('text', '')
steps = utils.get_images('static/img/pipelines/steps/{}'.format(folder))
steps.sort(key=lambda x: int(x[1].split(')')[0]))
results = []
for step in steps:
result_text, percentage = ocr.compare(text, utils.get_filepath('static/img/pipelines/steps/{}'.format(folder), step[1]))
results.append({'step': step[1].split('-')[0], 'original': text, 'result': result_text, 'percentage': percentage})
result_text, percentage = ocr.compare(text, filepath)
results.insert(0, {'step': 'original', 'original': text, 'result': result_text, 'percentage': percentage})
return jsonify(results)
def get_ocr(image):
filepath = utils.get_filepath(app.config['INPUT_FOLDER'], image)
if filepath is None:
return redirect(url_for('index'))
text = request.form.get('text', '')
pipelines = utils.get_images(app.config['OUTPUT_FOLDER_PIPELINES'])
pipelines.sort(key=lambda x: int(x[1].split('-')[0]))
results = []
for pipeline in pipelines:
result_text, percentage = ocr.compare(text, utils.get_filepath(app.config['OUTPUT_FOLDER_PIPELINES'], pipeline[1]))
results.append({'pipeline': pipeline[1].split('-')[0], 'original': text, 'result': result_text, 'percentage': percentage})
results = sorted(results, key=itemgetter('percentage'), reverse=True)
result_text, percentage = ocr.compare(text, filepath)
results.insert(0, {'pipeline': 'original', 'original': text, 'result': result_text, 'percentage': percentage})
return jsonify(results)
def get_ocr(image):
filepath = utils.get_filepath(app.config['INPUT_FOLDER'], image)
if filepath is None:
return not_found_error()
text = request.get_json().get('text')
if text is None:
response = jsonify({
'success': False,
'message': 'Field "text" is required'
})
response.status_code = 400
return response
pipelines = utils.get_images(app.config['OUTPUT_FOLDER_PIPELINES'])
pipelines.sort(key=lambda x: int(x[1].split('-')[0]))
results = []
for pipeline in pipelines:
result_text, percentage = ocr.compare(
text,
utils.get_filepath(app.config['OUTPUT_FOLDER_PIPELINES'],
pipeline[1]))
results.append({
'pipeline': pipeline[1].split('-')[0],
'original': text,
'result': result_text,
'percentage': percentage
})
results = sorted(results, key=itemgetter('percentage'), reverse=True)
result_text, percentage = ocr.compare(text, filepath)
results.insert(
0, {
'pipeline': 'original',
'original': text,
'result': result_text,
'percentage': percentage
})
response = jsonify({'success': True, 'results': results})
response.status_code = 200
return response
def get_ocr_steps(original, folder):
filepath = utils.get_filepath(app.config['INPUT_FOLDER'], original)
if filepath is None:
return not_found_error()
text = request.get_json().get('text')
if text is None:
response = jsonify({
'success': False,
'message': 'Field "text" is required'
})
response.status_code = 400
return response
steps = utils.get_images('static/img/pipelines/steps/{}'.format(folder))
steps.sort(key=lambda x: int(x[1].split(')')[0]))
results = []
for step in steps:
result_text, percentage = ocr.compare(
text,
utils.get_filepath('static/img/pipelines/steps/{}'.format(folder),
step[1]))
results.append({
'step': step[1].split('-')[0],
'original': text,
'result': result_text,
'percentage': percentage
})
result_text, percentage = ocr.compare(text, filepath)
results.insert(
0, {
'step': 'original',
'original': text,
'result': result_text,
'percentage': percentage
})
response = jsonify({'success': True, 'results': results})
response.status_code = 200
return response
def main(image=0):
if image == 0:
init__file_results()
images = utils.get_images(config['INPUT_FOLDER'])
images.sort(key=lambda x: int(x[1]))
images = images[image:]
for image in images:
print('Image {}'.format(image[1]))
filepath = image[0][1:]
text = ORIGINAL_TEXTS[image[1]]
utils.delete_images(config['OUTPUT_FOLDER_PIPELINES'])
time = default_timer()
result_text, percentage = ocr.compare(text, filepath)
time_end = default_timer() - time
write_file_result(
[image[1], 'original', percentage, text, result_text, time_end])
steps, times = processing_lib.pipeline(filepath,
config['TRANSFORMATIONS'])
pipelines = utils.get_images(config['OUTPUT_FOLDER_PIPELINES'])
for pipeline in pipelines:
time = default_timer()
result_text, percentage = ocr.compare(
text,
utils.get_filepath(config['OUTPUT_FOLDER_PIPELINES'],
pipeline[1]))
time_end = default_timer() - time
write_file_result([
image[1], '\r'.join(steps[int(pipeline[1].split('-')[0])]),
percentage, text, result_text,
times[int(pipeline[1].split('-')[0])] + time_end
])