1 files changed, 68 insertions, 0 deletions
diff --git a/megapixels/app/utils/identity_utils.py b/megapixels/app/utils/identity_utils.py
new file mode 100644
index 00000000..5b73a8e9
--- /dev/null
+++ b/megapixels/app/utils/identity_utils.py
@@ -0,0 +1,68 @@
+import os
+from pathlib import Path
+from glob import glob
+import unidecode
+import difflib
+
+from app.settings import types
+from app.utils import logger_utils
+
+log = logger_utils.Logger.getLogger()
+
+# Get list of names based on Dataset type
+def get_names(enum_dataset):
+  if enum_dataset == types.Dataset.LFW:
+    dir_lfw = '/data_store_hdd/datasets/people/lfw/media/original/'
+    names_orig = [x for x in os.listdir(dir_lfw)]
+    names_query = [x.replace('_', ' ') for x in names_orig]
+    result = {'names_orig': names_orig, 'names_query': names_query}
+  elif enum_dataset == types.Dataset.YOUTUBE_FACES:
+    names = [x for x in names if 'labeled faces.txt' not in x]
+  else:
+    log.warn(f'{enum_dataset} not yet implemented')
+    result = {}
+  return result
+
+def similarity(a, b):
+  return difflib.SequenceMatcher(a=a.lower(), b=b.lower()).ratio()
+
+def names_match(name_a, name_b, threshold=0.9, as_float=False, compound_score=False):
+  '''Returns boolean if names are similar enough
+  '''
+  # strip spaces and split names into list of plain text words
+  name_a_clean = [unidecode.unidecode(x.strip().lower()) for x in name_a.strip().split(' ')]
+  name_b_clean = [unidecode.unidecode(x.strip().lower()) for x in name_b.strip().split(' ')]
+  
+  # assign short long vars
+  len_a = len(name_a_clean)
+  len_b = len(name_b_clean)
+  len_min = min(len_a, len_b)
+  len_max = max(len_a, len_b)
+  
+  # compute scores
+  scores = []
+  for i in range(len(name_a_clean)):
+    word_a = name_a_clean[i]
+    subscores = []
+    for j in range(len(name_b_clean)):
+      word_b = name_b_clean[j]
+      score = similarity(word_a, word_b)
+      subscores.append(score)
+    scores.append(subscores)
+  
+  # return result
+  ratio_similar = sum(max(x) for x in scores) / len_min
+  # combine with any missing letters/words
+  letters_a = sum(len(x) for x in name_a_clean)
+  letters_b = sum(len(x) for x in name_b_clean)
+  ratio_letters = min(letters_a, letters_b) / max(letters_a, letters_b)
+
+  if compound_score:
+    score = (0.8 * ratio_similar) + (0.2 * ratio_letters)
+  else:
+    score = ratio_similar
+
+  if as_float:
+    return score
+  else:
+    return score > threshold
+\ No newline at end of file