Hello,WeR17;re doing research for our final year project. Our project subject is; Artificial intelligence and image Processing
**Client:**Camera frames will be sent to the server (API) in real time using the phone’s camera only. We going to use the client software to send only the frames and draw the incoming data to the screen. We set the number of frames to be processed in seconds with the tickrate that we set on the client. The camera must be on continuously and the boxes (face) on the screen should be updated whenever incoming new coordinates are received.
All communications between the server and the client will be done with the help of an API.
**Server:**We want to perform all image processing on the server. The frames sent by the client will be processed here and converted to the JSON format. (Face coordinats, Body coordinats, etc.) The server will wait for the frame to arrive from the API and process it when it arrives.
**The Main Questions:**In short of story, using the phone camera, we want to find faces by making image processing on the server and drawing incoming (from Server>API>Client) coordinates on the screen.
We are using:Server: Python, Tensorflow, OpenCV,Client: ReactNative (Phone)?
In what format should the incoming and outgoing data be communicated? (JSON, XML etc)
How to do the server-client architecture should be exactly? (Wireless Communication)
Are there any similar projects?
Do you have any suggestions for solving this problem?
Edit: Like Intelligent Kiosk: https://blogs.technet.microsoft.com/msuspartner/2016/10/31/data-analytics-intelligent-kiosk-demo/ 🙂