diff --git a/README.md b/README.md
index 910324f..ff95c6e 100644
--- a/README.md
+++ b/README.md
@@ -164,7 +164,7 @@ for backend in backends:
 
 <p align="center"><img src="https://raw.githubusercontent.com/serengil/deepface/master/icon/deepface-detectors.png" width="90%" height="90%"></p>
 
-[RetinaFace](https://sefiks.com/2021/04/27/deep-face-detection-with-retinaface-in-python/) and [MTCNN](https://sefiks.com/2020/09/09/deep-face-detection-with-mtcnn-in-python/) seem to overperform in detection and alignment stages but they are slower than others.
+[RetinaFace](https://sefiks.com/2021/04/27/deep-face-detection-with-retinaface-in-python/) and [MTCNN](https://sefiks.com/2020/09/09/deep-face-detection-with-mtcnn-in-python/) seem to overperform in detection and alignment stages but they are slower than others. If the speed of your pipeline is more important, then you should use opencv or ssd. On the other hand, accuracy is more important than the speed, then you should use retinaface or mtcnn.
 
 **Tech Stack** - [`Vlog`](https://youtu.be/R8fHsL7u3eE)