Khadas Docs

Amazing Khadas, always amazes you!

User Tools

Site Tools


products:sbc:edge2:npu:demos:face-recognition

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
products:sbc:edge2:npu:demos:face-recognition [2023/10/12 04:12]
sravan [Face Recognition VIM4 Demo - 7]
products:sbc:edge2:npu:demos:face-recognition [2025/04/09 23:43] (current)
louis
Line 4: Line 4:
  
 {{indexmenu_n>7}} {{indexmenu_n>7}}
 +
 +===== Introduction =====
 +
 +Face Recognition Demo consists of two models, RetinaFace and FaceNet. It can detect face on image and recognize who it is. Here are two judgment indicators, cosine similarity and Euclidean distance. The closer the cosine similarity is to 1 and the closer the Euclidean distance is to 0, the more similar is between two faces.
 +
 +Here takes **lin_1.jpg** as example. Inference results on Edge2. Only show cosine similarity.
 +
 +{{:products:sbc:edge2:npu:demos:face-recognition-result.png?200|}} {{:products:sbc:edge2:npu:demos:result.jpg?400|}}
 +
 +**Inference speed test**: USB camera about **44ms** per frame. MIPI camera about **33ms** per frame.
  
 <WRAP important > <WRAP important >
Line 62: Line 72:
  
 ```shell ```shell
-# Run+# Run USB camera
 $ cd install/retinaface_cap $ cd install/retinaface_cap
-$ ./face_recognition data/model/retinaface.rknn data/model/facenet.rknn 33+$ ./face_recognition data/model/retinaface.rknn data/model/facenet.rknn usb 60 
 + 
 +# Run MIPI camera 
 +$ cd install/retinaface_cap 
 +$ ./face_recognition data/model/retinaface.rknn data/model/facenet.rknn mipi 42
 ``` ```
  
-''33'' is camera device index.+<WRAP info > 
 +''60'' and ''42'' are camera device index. 
 +</WRAP> 
Last modified: 2025/04/09 23:43 by louis