def test_get_tag_from_image_with_threshold(self):
image_path = ('..' + os.sep + 'test_files' + os.sep +
'caption_recognition' + os.sep + 'Test.jpg')
tags_file_path = ('..' + os.sep + 'test_files' + os.sep +
'caption_recognition' + os.sep + 'Tags.txt')
params = {c.USE_LEVENSHTEIN_KEY: True, c.LEV_RATIO_PCT_THRESH_KEY: 0.99,
c.MIN_TAG_LENGTH_KEY: 0, c.USE_BLACKLIST_KEY: False,
c.TAGS_FILE_PATH_KEY: tags_file_path}
result_dict = get_tag_from_image(image_path, params)
assigned_tag = result_dict[c.ASSIGNED_TAG_KEY]
# Assigned tag for this image must be undefined
self.assertEquals(assigned_tag, c.UNDEFINED_TAG)
eq_letters_nr = result_dict[c.EQ_LETTERS_NR_KEY]
tot_letters_nr = result_dict[c.TOT_LETTERS_NR_KEY]
self.assertTrue(eq_letters_nr <= tot_letters_nr)
def test_get_tag_from_image(self):
image_path = ('..' + os.sep + 'test_files' + os.sep +
'caption_recognition' + os.sep + 'Test.jpg')
tags_file_path = ('..' + os.sep + 'test_files' + os.sep +
'caption_recognition' + os.sep + 'Tags.txt')
tags = get_tags_from_file(tags_file_path)
params = {c.USE_LEVENSHTEIN_KEY: True, c.LEV_RATIO_PCT_THRESH_KEY: 0,
c.MIN_TAG_LENGTH_KEY: 0, c.USE_BLACKLIST_KEY: False,
c.TAGS_FILE_PATH_KEY: tags_file_path}
result_dict = get_tag_from_image(image_path, params)
assigned_tag = result_dict[c.ASSIGNED_TAG_KEY]
# Threshold and blacklist are not used,
# so assigned tag must be in tags file
self.assertIn(assigned_tag, tags)
eq_letters_nr = result_dict[c.EQ_LETTERS_NR_KEY]
tot_letters_nr = result_dict[c.TOT_LETTERS_NR_KEY]
self.assertTrue(eq_letters_nr <= tot_letters_nr)
def analyze_image(image_path, params=None):
"""
Execute caption recognition on given image
:type image_path: string
:param image_path: path of image to be analyzed
:type params: dictionary
:param params: configuration parameters (see table)
:rtype: tuple
:returns: a (label, tag, face) tuple,
where label is the assigned label,
tag the assigned tag
and face the detected face in image (as an OpenCV image)
============================================ ======================================== =============================
Key Value Default value
============================================ ======================================== =============================
align_path Path of directory
where aligned faces are saved
check_eye_positions If True, check eye positions True
classifiers_dir_path Path of directory with OpenCV
cascade classifiers
eye_detection_classifier Classifier for eye detection 'haarcascade_mcs_lefteye.xml'
face_detection_algorithm Classifier for face detection 'HaarCascadeFrontalFaceAlt2'
('HaarCascadeFrontalFaceAlt',
'HaarCascadeFrontalFaceAltTree',
'HaarCascadeFrontalFaceAlt2',
'HaarCascadeFrontalFaceDefault',
'HaarCascadeProfileFace',
'HaarCascadeFrontalAndProfileFaces',
'HaarCascadeFrontalAndProfileFaces2',
'LBPCascadeFrontalface',
'LBPCascadeProfileFace' or
'LBPCascadeFrontalAndProfileFaces')
flags Flags used in face detection 'DoCannyPruning'
('DoCannyPruning', 'ScaleImage',
'FindBiggestObject', 'DoRoughSearch').
If 'DoCannyPruning' is used, regions
that do not contain lines are discarded.
If 'ScaleImage' is used, image instead
of the detector is scaled
(it can be advantegeous in terms of
memory and cache use).
If 'FindBiggestObject' is used,
only the biggest object is returned
by the detector.
'DoRoughSearch', used together with
'FindBiggestObject',
terminates the search as soon as
the first candidate object is found
min_neighbors Mininum number of neighbor bounding 5
boxes for retaining face detection
min_size_height Minimum height of face detection 20
bounding box (in pixels)
min_size_width Minimum width of face detection 20
bounding box (in pixels)
scale_factor Scale factor between two scans 1.1
in face detection
max_eye_angle Maximum inclination of the line 0.125
connecting the eyes
(in % of pi radians)
min_eye_distance Minimum distance between eyes 0.25
(in % of the width of the face
bounding box)
nose_detection_classifier Classifier for nose detection 'haarcascade_mcs_nose.xml'
software_test_file Path of image to be used for
software test
use_nose_pos_in_detection If True, detections with no good False
nose position are discarded
lev_ratio_pct_threshold Minimum threshold for considering 0.8
captions in frame
min_tag_length Minimum length of tags considered 10
in caption recognition
tags_file_path Path of text file containing
list of tags
tesseract_parent_dir_path Path of directory containing
'tesseract' directory
use_blacklist If True, use blacklist of items True
that make the results of the
caption recognition on a frame
rejected
use_levenshtein If True, words found in image True
by caption recognition and tags
are compared by using
the Levenshtein distance
============================================ ======================================== =============================
"""
label = -1
tag = -1
align_path = c.ALIGNED_FACES_PATH
if (params is not None) and (c.ALIGNED_FACES_PATH_KEY in params):
align_path = params[c.ALIGNED_FACES_PATH_KEY]
# Face detection
face = get_detected_cropped_face(image_path, align_path, params)
if face is not None:
cap_rec_res = get_tag_from_image(image_path, params)
label = cap_rec_res[c.ASSIGNED_LABEL_KEY]
tag = cap_rec_res[c.ASSIGNED_TAG_KEY]
return label, tag, face
def caption_experiments(params=None):
"""
Execute caption recognition experiments
:type params: dictionary
:param params: configuration parameters
to be used for the experiment (see table)
============================================ ======================================== ==============
Key Value Default value
============================================ ======================================== ==============
test_set_path Path of directory containing test set
lev_ratio_pct_threshold Minimum threshold for considering 0.8
captions in frame
min_tag_length Minimum length of tags considered 10
in caption recognition
tags_file_path Path of text file containing
list of tags
tesseract_parent_dir_path Path of directory containing
'tesseract' directory
use_blacklist If True, use blacklist of items True
that make the results of the
caption recognition on a frame
rejected
use_levenshtein If True, words found in image True
by caption recognition and tags
are compared by using
the Levenshtein distance
============================================ ======================================== ==============
"""
test_set_path = ce.CAPTION_RECOGNITION_TEST_SET_PATH
if params is not None:
if ce.TEST_SET_PATH_KEY in params:
test_set_path = params[ce.TEST_SET_PATH_KEY]
# Iterate over all directories with images
rec_rate_list = []
conf_list = []
time_list = []
for images_dir in os.listdir(test_set_path):
ann_tag = images_dir
images_dir_complete_path = os.path.join(
test_set_path, images_dir)
true_pos_nr = 0.0
person_test_images_nr = 0.0
for image in os.listdir(images_dir_complete_path):
image_complete_path = os.path.join(
images_dir_complete_path, image)
start_time = cv2.getTickCount()
result_dict = get_tag_from_image(
image_complete_path, params)
time_in_clocks = cv2.getTickCount() - start_time
time_in_seconds = time_in_clocks / cv2.getTickFrequency()
time_list.append(time_in_seconds)
assigned_tag = result_dict[c.ASSIGNED_TAG_KEY]
conf = result_dict[c.CONFIDENCE_KEY]
if assigned_tag == ann_tag:
true_pos_nr += 1
conf_list.append(conf)
person_test_images_nr += 1
rec_rate = true_pos_nr / person_test_images_nr
rec_rate_list.append(rec_rate)
mean_rec_rate = float(numpy.mean(rec_rate_list))
std_rec_rate = float(numpy.std(rec_rate_list))
mean_conf = float(numpy.mean(conf_list))
mean_time = float(numpy.mean(time_list))
print("\n ### RESULTS ###\n")
print('Mean of recognition rate: ' + str(mean_rec_rate))
print('Standard deviation of recognition rate: ' + str(std_rec_rate))
print('Mean of confidence in true positives: ' + str(mean_conf))
print('Mean analysis time: ' + str(mean_time) + ' s')
