Add tolerance parameter to CLI

ageitgey · ageitgey · commit b8a803731c23 · 2017-08-03T11:25:11.000-07:00
diff --git a/README.md b/README.md
@@ -130,6 +130,20 @@ with the filename and the name of the person found.
 An `unknown_person` is a face in the image that didn't match anyone in
 your folder of known people.
 
+If you are getting multiple matches for the same person, it might be that
+the people in your photos look very similar and a lower tolerance value
+is needed to make face comparisons more strict.
+
+You can do that with the `--tolerance` parameter. The default tolerance
+value is 0.6 and lower numbers make face comparisons more strict:
+
+```bash
+$ face_recognition --tolerance 0.54 ./pictures_of_people_i_know/ ./unknown_pictures/
+
+/unknown_pictures/unknown.jpg,Barack Obama
+/face_recognition_test/unknown_pictures/unknown.jpg,unknown_person
+```
+
 If you simply want to know the names of the people in each photograph but don't
 care about file names, you could do this:
 
diff --git a/face_recognition/cli.py b/face_recognition/cli.py
@@ -32,7 +32,7 @@ def scan_known_people(known_people_folder):
     return known_names, known_face_encodings
 
 
-def test_image(image_to_check, known_names, known_face_encodings):
+def test_image(image_to_check, known_names, known_face_encodings, tolerance=0.6):
     unknown_image = face_recognition.load_image_file(image_to_check)
 
     # Scale down image if it's giant so things run a little faster
@@ -45,7 +45,7 @@ def test_image(image_to_check, known_names, known_face_encodings):
     unknown_encodings = face_recognition.face_encodings(unknown_image)
 
     for unknown_encoding in unknown_encodings:
-        result = face_recognition.compare_faces(known_face_encodings, unknown_encoding)
+        result = face_recognition.compare_faces(known_face_encodings, unknown_encoding, tolerance=tolerance)
 
         if True in result:
             [print("{},{}".format(image_to_check, name)) for is_match, name in zip(result, known_names) if is_match]
@@ -57,7 +57,7 @@ def image_files_in_folder(folder):
     return [os.path.join(folder, f) for f in os.listdir(folder) if re.match(r'.*\.(jpg|jpeg|png)', f, flags=re.I)]
 
 
-def process_images_in_process_pool(images_to_check, known_names, known_face_encodings, number_of_cpus):
+def process_images_in_process_pool(images_to_check, known_names, known_face_encodings, number_of_cpus, tolerance):
     if number_of_cpus == -1:
         processes = None
     else:
@@ -69,7 +69,7 @@ def process_images_in_process_pool(images_to_check, known_names, known_face_enco
         context = multiprocessing.get_context("forkserver")
 
     pool = context.Pool(processes=processes)
-    function_parameters = zip(images_to_check, itertools.repeat(known_names), itertools.repeat(known_face_encodings))
+    function_parameters = zip(images_to_check, itertools.repeat(known_names), itertools.repeat(known_face_encodings),  itertools.repeat(tolerance))
 
     pool.starmap(test_image, function_parameters)
 
@@ -78,7 +78,8 @@ def process_images_in_process_pool(images_to_check, known_names, known_face_enco
 @click.argument('known_people_folder')
 @click.argument('image_to_check')
 @click.option('--cpus', default=1, help='number of CPU cores to use in parallel (can speed up processing lots of images). -1 means "use all in system"')
-def main(known_people_folder, image_to_check, cpus):
+@click.option('--tolerance', default=0.6, help='Tolerance to use for face comparisons. Default is 0.6 and lower is more strict matching. Lower this if you get multiple matches for the same person. Try 0.54 for example.')
+def main(known_people_folder, image_to_check, cpus, tolerance):
     known_names, known_face_encodings = scan_known_people(known_people_folder)
 
     # Multi-core processing only supported on Python 3.4 or greater
@@ -88,9 +89,9 @@ def main(known_people_folder, image_to_check, cpus):
 
     if os.path.isdir(image_to_check):
         if cpus == 1:
-            [test_image(image_file, known_names, known_face_encodings) for image_file in image_files_in_folder(image_to_check)]
+            [test_image(image_file, known_names, known_face_encodings, tolerance) for image_file in image_files_in_folder(image_to_check)]
         else:
-            process_images_in_process_pool(image_files_in_folder(image_to_check), known_names, known_face_encodings, cpus)
+            process_images_in_process_pool(image_files_in_folder(image_to_check), known_names, known_face_encodings, cpus, tolerance)
     else:
         test_image(image_to_check, known_names, known_face_encodings)
 
diff --git a/tests/test_face_recognition.py b/tests/test_face_recognition.py
@@ -183,7 +183,7 @@ def test_compare_faces_empty_lists(self):
         self.assertListEqual(match_results, [])
 
     def test_command_line_interface_options(self):
-        target_string = '--help          Show this message and exit.'
+        target_string = '--help             Show this message and exit.'
         runner = CliRunner()
         help_result = runner.invoke(cli.main, ['--help'])
         self.assertEqual(help_result.exit_code, 0)
@@ -195,7 +195,18 @@ def test_command_line_interface(self):
         image_folder = os.path.join(os.path.dirname(__file__), 'test_images')
         image_file = os.path.join(os.path.dirname(__file__), 'test_images', 'obama.jpg')
 
-        help_result = runner.invoke(cli.main, args=[image_folder, image_file])
+        result = runner.invoke(cli.main, args=[image_folder, image_file])
 
-        self.assertEqual(help_result.exit_code, 0)
-        self.assertTrue(target_string in help_result.output)
+        self.assertEqual(result.exit_code, 0)
+        self.assertTrue(target_string in result.output)
+
+    def test_command_line_interface_tolerance(self):
+        target_string = 'obama.jpg,obama'
+        runner = CliRunner()
+        image_folder = os.path.join(os.path.dirname(__file__), 'test_images')
+        image_file = os.path.join(os.path.dirname(__file__), 'test_images', 'obama.jpg')
+
+        result = runner.invoke(cli.main, args=[image_folder, image_file, "--tolerance", "0.55"])
+
+        self.assertEqual(result.exit_code, 0)
+        self.assertTrue(target_string in result.output)
