use COLOR_BGR2RGB

examples/blink_detection.py

@@ -25,7 +25,7 @@ def main():
     ret, frame = video_capture.read(0)
     # cv2.VideoCapture.release()
     small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25)
-    rgb_small_frame = small_frame[:, :, ::-1]
+    rgb_small_frame = cv2.cvtColor(small_frame, cv2.COLOR_BGR2RGB)
 
     face_landmarks_list = face_recognition.face_landmarks(rgb_small_frame)
     process = True
@@ -35,12 +35,12 @@ def main():
 
         # get it into the correct format
         small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25)
-        rgb_small_frame = small_frame[:, :, ::-1]
+        rgb_small_frame = cv2.cvtColor(small_frame, cv2.COLOR_BGR2RGB)
 
 
 
         # get the correct face landmarks
-        
+
         if process:
             face_landmarks_list = face_recognition.face_landmarks(rgb_small_frame)
 
@@ -73,7 +73,7 @@ def main():
                     while (asleep): #continue this loop until they wake up and acknowledge music
                         print("EYES CLOSED")
 
-                        if cv2.waitKey(1) == 32: #Wait for space key  
+                        if cv2.waitKey(1) == 32: #Wait for space key
                             asleep = False
                             print("EYES OPENED")
                     closed_count = 0
@@ -89,14 +89,14 @@ def get_ear(eye):
 	# vertical eye landmarks (x, y)-coordinates
 	A = dist.euclidean(eye[1], eye[5])
 	B = dist.euclidean(eye[2], eye[4])
- 
+
 	# compute the euclidean distance between the horizontal
 	# eye landmark (x, y)-coordinates
 	C = dist.euclidean(eye[0], eye[3])
- 
+
 	# compute the eye aspect ratio
 	ear = (A + B) / (2.0 * C)
- 
+
 	# return the eye aspect ratio
 	return ear
 

examples/facerec_from_video_file.py

@@ -43,7 +43,7 @@
         break
 
     # Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
-    rgb_frame = frame[:, :, ::-1]
+    rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
 
     # Find all the faces and face encodings in the current frame of video
     face_locations = face_recognition.face_locations(rgb_frame)

examples/facerec_from_webcam.py

@@ -35,7 +35,7 @@
     ret, frame = video_capture.read()
 
     # Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
-    rgb_frame = frame[:, :, ::-1]
+    rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
 
     # Find all the faces and face enqcodings in the frame of video
     face_locations = face_recognition.face_locations(rgb_frame)

examples/facerec_from_webcam_faster.py

@@ -48,8 +48,8 @@
         small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25)
 
         # Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
-        rgb_small_frame = small_frame[:, :, ::-1]
-        
+        rgb_small_frame = cv2.cvtColor(small_frame, cv2.COLOR_BGR2RGB)
+
         # Find all the faces and face encodings in the current frame of video
         face_locations = face_recognition.face_locations(rgb_small_frame)
         face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations)

examples/facerec_from_webcam_multiprocessing.py

@@ -78,7 +78,7 @@ def process(worker_id, read_frame_list, write_frame_list, Global, worker_num):
         Global.read_num = next_id(Global.read_num, worker_num)
 
         # Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
-        rgb_frame = frame_process[:, :, ::-1]
+        rgb_frame = cv2.cvtColor(frame_process, cv2.COLOR_BGR2RGB)
 
         # Find all the faces and face encodings in the frame of video, cost most time
         face_locations = face_recognition.face_locations(rgb_frame)

examples/find_faces_in_batches.py

@@ -29,7 +29,7 @@
         break
 
     # Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
-    frame = frame[:, :, ::-1]
+    frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
 
     # Save each frame of the video to a list
     frame_count += 1