Queen: Mirror, mirror, on the wall, who is the fairest of them all?
Mirror: My Queen, you are the fairest in the land.
-- Magic Mirror(Snow White)
| Role | Name | Bio | |
|---|---|---|---|
| President | Meina SONG | ||
| Project Manager | Xin HE | [email protected] | |
| Chief Architect | Huan LI | [email protected] | Magic Mirror Project Initializer |
| Task System Manager | Shenda SHI | [email protected] | |
| System Administrator | Wenjun CHAI | ||
| CV Engineer | Bo LIN | [email protected] | |
| CV Engineer | Qing DONG | [email protected] | |
| CV Engineer | Jiaming DUAN | [email protected] | |
| Multi-Modal Engineer | Zhengyuan ZHU | [email protected] | |
| Multi-Modal Engineer | Guang CHEN | [email protected] | |
| Dialog Engineer | Qinghua DUAN | [email protected] | |
| Vision Engineer | Zhenggang HOU | ||
| System Engineer | TBH | ||
| UI Designer | TBH |
Requirements:
- Eager willing to learning Machine Learning.
- Strong sense of responsibility.
- Good team player.
- Ability to contribute at least 4 hour per week, which including 1 hour for team communition, 2 hour researching, and 1 hour for coding/docing.
Join us by contact @huan (Wechat: 918999) if you are interested!
This idea is created from @huan on Dec 2017, and write a slide from scratch.
- Oct: The controller of the screen had been upgraded so that it can work without any additional hardward. (we don't need to use another computer to setup the screen after it turned on any more)
- Nov: We added a HDMI switcher to manage multiple input signals so that we can do switch as easy as push a button.
- Dec: We had setup Audio System for the Screen so that the HDMI audio can be played as well.
We are setting up the team of the project Magic Mirror!
Currently we have 3 members: Professor SONG, PhD LI, and Master CHAI, we are HIRING!
- Setup the Cameras!
- Setup the Microphones!
- Record the Videos & Audios, and the ability to play them back.
- Integrate PoseNet & FaceNet with Cameras, so that the Mirror could be able to tell us the following facts:
- How many people are in the room
- Who are in the room
- Who are raising their hands
- Who are lower their heads
- Integrate Audio Speech Recognition with Microphones, so that the Mirror could be able to do the following tasks:
- Generate the Text Subtitle in real time
- Develop our own algrithms to do ASR (optional)
- Integrate Text to Speech so that the Mirror can Talk:
- Integrate with TTS API
- Develop our own algrithms like WaveNet (optional)
- Integrate Mirror with Wechat: Mirror will be able to talk with you on Wechat!
- Other Models
- Body-Pix
- Finger-Net
Do something BIG!
- Homo - 一个高性能，易于扩展且完全开源的自然交互系统
- Carnegie Mellon University - 2015 Fall: The Databaseology Lecture Series > RocksDB
Huan LI (李卓桓) <[email protected]>
- Code & Docs © 2017-2019 Huan LI <[email protected]>
- Code released under the Apache-2.0 License
- Docs released under Creative Commons