talksik/mediapipe
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Project import generated by Copybara.

Browse Source 
GitOrigin-RevId: 612e50bb8db2ec3dc1c30049372d87a80c3848db
This commit is contained in:
MediaPipe Team
2020-08-30 19:52:55 -04:00
committed by chuoling
parent a7225b938a
commit c0124fb83c
248 changed files with 5225 additions and 1914 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/solutions/iris.md
+6 -1
View File
@@ -55,7 +55,7 @@ that uses a
from the
[face landmark module](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_landmark),
an
[iris landmark subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/iris_tracking/iris_landmark_left_and_right_gpu.pbtxt)
[iris landmark subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/iris_landmark/iris_landmark_left_and_right_gpu.pbtxt)
from the
[iris landmark module](https://github.com/google/mediapipe/tree/master/mediapipe/modules/iris_landmark),
and renders using a dedicated
@@ -72,6 +72,11 @@ Note: To visualize a graph, copy the graph and paste it into
to visualize its associated subgraphs, please see
[visualizer documentation](../tools/visualizer.md).
The output of the pipeline is a set of 478 3D landmarks, including 468 face
landmarks from [MediaPipe Face Mesh](./face_mesh.md), with those around the eyes
further refined (see Fig 2), and 10 additional iris landmarks appended at the
end (5 for each eye, and see Fig 2 also).
## Models
### Face Detection Model