diff --git a/README.md b/README.md
index 8f7ed78..2946c71 100644
--- a/README.md
+++ b/README.md
@@ -1,72 +1,68 @@
-# Mobilefacenet Face Landmark Detecter
+# MobileFaceNet Face Landmark Detecter
 
 *authors: David Wang*
 
 
 ## Desription
 
-A class of extremely efficient CNN models to extract 68 landmarks from a facial image[MobileFaceNets](https://arxiv.org/pdf/1804.07573.pdf).
+[MobileFaceNets](https://arxiv.org/pdf/1804.07573) is a class of extremely efficient CNN models to extract 68 landmarks from a facial image, which use less than 1 million parameters and are specifically tailored for high-accuracy real-time face verification on mobile and embedded devices. This repo is an adaptation from [cuijian/pytorch_face_landmark](https://github.com/cunjian/pytorch_face_landmark).
 
 ## Code Example
 
-extracted facial landmark from './img1.jpg'. 
+Extract facial landmarks from './img1.jpg'. 
 
 *Write the pipeline in simplified style*:
 
 ```python
-from towhee import dc
+import towhee
 
-dc.glob('./img1.jpg') \
+towhee.glob('./img1.jpg') \
+  .image_decode.cv2() \
   .face_landmark_detection.mobilefacenet() \
+  .select('img','landmark') \
   .to_list()
 ```
 
 *Write a same pipeline with explicit inputs/outputs name specifications:*
 
 ```python
-from towhee import dc
+import towhee
 
-dc.glob['path']('./img1.jpg') \
+towhee.glob['path']('./img1.jpg') \
   .image_decode.cv2['path', 'img']() \
-  .face_landmark_detection.mobilefacenet() \
-  .to_list()
+  .face_landmark_detection.mobilefacenet['img', 'landmark']() \
+  .select('img','landmark') \
+  .show()
 ```
 
+<img src="https://towhee.io/face-landmark-detection/mobilefacenet/raw/branch/main/result.png" alt="result1" style="height:20px;"/>
+
 ## Factory Constructor
 
 Create the operator via the following factory method
 
-***ops.face_landmark_detection.mobilefacenet(pretrained = True)***
+***face_landmark_detection.mobilefacenet(pretrained = True)***
 
 **Parameters:**
 
 ​  ***pretrained***
 
-​  whether load the pretrained weights..
+​  whether load the pretrained weights.
 
-​  supported types: `bool`, default is True, using pretrained weights
+​  supported types: `bool`, default is True, using pretrained weights.
 
 ## Interface
 
 An image embedding operator takes an image as input. it extracts the embedding back to ndarray.
 
-**Args:**
-
-​  ***pretrained***
-
-​  whether load the pretrained weights..
-
-​  supported types: `bool`, default is True, using pretrained weights
-
-
 **Parameters:**
 
-​	***image***: *np.ndarray*
+​	***img***: *towhee.types.Image (a sub-class of numpy.ndarray)*
 
 ​	The input image.
 
 
-**Returns:**: *numpy.ndarray*
+**Returns:** *numpy.ndarray*	
 
-​	The extracted facial landmark.
+​	The extracted facial landmarks.
 
diff --git a/__init__.py b/__init__.py
index 6136253..ac8dd1a 100644
--- a/__init__.py
+++ b/__init__.py
@@ -14,6 +14,6 @@
 
 from .mobilefacenet import Mobilefacenet
 
-def mobilefacenet():
-    return Mobilefacenet()
+def mobilefacenet(pretrained = True):
+    return Mobilefacenet(pretrained)
 
diff --git a/mobilefacenet.py b/mobilefacenet.py
index e8a472d..571795b 100644
--- a/mobilefacenet.py
+++ b/mobilefacenet.py
@@ -54,8 +54,8 @@ class Mobilefacenet(NNOperator):
                                         normalize])
 
     @arg(1, to_image_color('RGB') )
-    def __call__(self, image: Image):
-        image = to_pil(image)
+    def __call__(self, img: Image):
+        image = to_pil(img)
         h, w = image.size
         tensor = self._preprocess(image)
         if len(tensor.shape) == 3:
diff --git a/result.png b/result.png
new file mode 100644
index 0000000..065bece
Binary files /dev/null and b/result.png differ