def get_features(self, label):
test_dataset_folder_path = os.path.abspath(
os.path.join(Path(os.getcwd()).parent, self.labelled_dataset_path))
images_list = list(
misc.get_images_in_directory(test_dataset_folder_path).keys())
metadata = Metadata(images_list)
if self.feature_name != 'SIFT':
metadata.save_label_decomposed_features(label,
self.decomposed_feature)
features = misc.load_from_pickle(
self.reduced_pickle_file_folder,
self.decomposed_feature + '_' + label)
else:
features = {}
database_features = misc.load_from_pickle(
self.main_pickle_file_folder, self.feature_name)
label_images_list = metadata.get_specific_metadata_images_list(
feature_dict={'aspectOfHand': label})
for image in label_images_list:
features[image] = database_features[image]
return features
},
5: {
"accessories": 1
},
6: {
"accessories": 0
},
7: {
"gender": "male"
},
8: {
"gender": "female"
}
}
metadata_images_list = metadata.get_specific_metadata_images_list(
label_interpret_dict.get(label))
k = int(input("Please specify the number of components : "))
metadata_label = ''
for key, value in label_interpret_dict.get(label).items():
metadata_label = key + '_' + str(value)
decomposition = Decomposition(decomposition_model,
k,
model,
test_dataset_path,
metadata_images_list=metadata_images_list,
metadata_label=metadata_label)
decomposition.dimensionality_reduction()
elif task == '4':
model = input("1.CM\n2.LBP\n3.HOG\n4.SIFT\nSelect model: ")
decomposition_model = input(
labelled_dataset_path = input('Enter labelled dataset path: ')
unlabelled_dataset_path = input('Enter unlabelled dataset path: ')
label_feature_name = 'LBP'
if classifier == 'DT':
label_feature_name = 'LBP'
elif classifier == 'PPR':
label_feature_name = 'HOG'
result = {}
print('Getting Labeled Image features from Phase 1')
label_folder_features = helper_functions.get_main_features(
label_feature_name, labelled_dataset_path)
metadata = Metadata(list(label_folder_features.keys()),
metadatapath='Data/HandInfo.csv')
dorsal_images_list = metadata.get_specific_metadata_images_list(
{'aspectOfHand': 'dorsal'})
palmar_images_list = metadata.get_specific_metadata_images_list(
{'aspectOfHand': 'palmar'})
print('Getting unlabelled image features from Phase 1')
unlabelled_features = helper_functions.get_main_features(
label_feature_name, unlabelled_dataset_path)
dorsal_features = {}
palmar_features = {}
for image in dorsal_images_list:
dorsal_features[image] = label_folder_features[image]
for image in palmar_images_list:
palmar_features[image] = label_folder_features[image]
