Difference between revisions of "Minh Pham - FaceTune"
From vjmedia
| (4 intermediate revisions by the same user not shown) | |||
| Line 9: | Line 9: | ||
Install Dependencies: | Install Dependencies: | ||
| − | pip install python-osc | + | |
| − | pip3 install mtcnn | + | pip install python-osc |
| + | |||
| + | pip3 install mtcnn | ||
| + | |||
pip3 install tensorflow==1.4.1 opencv-contrib-python==3.2.0.8 | pip3 install tensorflow==1.4.1 opencv-contrib-python==3.2.0.8 | ||
| + | |||
pip3 install tensorflow-gpu\>=1.4.0 | pip3 install tensorflow-gpu\>=1.4.0 | ||
| + | |||
""Workflow of FaceTune"" | ""Workflow of FaceTune"" | ||
| + | |||
- Implement MTCNN to detect and capture face. | - Implement MTCNN to detect and capture face. | ||
- Process and store only the unique RGB values of the image. | - Process and store only the unique RGB values of the image. | ||
| Line 20: | Line 26: | ||
---- | ---- | ||
| − | |||
https://vjmedia.wpi.edu/File:Final_proj.mp4 | https://vjmedia.wpi.edu/File:Final_proj.mp4 | ||
Latest revision as of 19:00, 11 October 2019
FaceTune is a software that will create sound based on your face.
Hardware:
-Mac or PC
Software:
Install Dependencies:
pip install python-osc
pip3 install mtcnn
pip3 install tensorflow==1.4.1 opencv-contrib-python==3.2.0.8
pip3 install tensorflow-gpu\>=1.4.0
""Workflow of FaceTune""
- Implement MTCNN to detect and capture face. - Process and store only the unique RGB values of the image. - Use Object Sound Control to transfer data to MAXMSP.