Snapuskin
- 0 Collaborators
It's a portable device that can identify what skin diseases that we are suffering from with the help of a camera on it. we can simply do this concept on mobile devices but once we've tried the same we haven't satisfied with the accuracy because the input is even biased with the lights, shades of the environment that we are taking pictures from. so this might be a closed camera with a proper single channel light on it. so we can easily collect the dataset from the same device and then we can train it with the dataset that we've collected from the device ...learn more
Project status: Under Development
Mobile, Robotics, Internet of Things, Artificial Intelligence
Groups
Internet of Things,
Student Developers for AI
Intel Technologies
OpenVINO,
Intel Opt ML/DL Framework
Overview / Usage
When I've tried to solve this problem with a mobile app it went wrong. that's why I made a thought like this. like to develop a portable device using a raspberry pi with a camera and a hardware accelerator in it to run the neural net within the raspberry pi. what this device is doing is it input an image that taken from a covered camera of the device. the light we are a standard, it will be remain same all the time. we are using tensorflow,caffe,openvino here
Methodology / Approach
i used tensorflow to develop a model for testing then i've moved to yolo. the worst thing is i'm putting a lot of time on annotating the data. i used intel cloud as a jupyternotebook . but now i' using colab to do development . when i have trying to train my model it's took a lot of time and expenses.
Technologies Used
technology : we are focusing on building the model so it's usually Dl things
frameworks:tensorflow,openvino,caffe,yolo
hardware: raspberry pi , intel movidious neural computation kit, camera, display, IR camera for the raspberry pi,some led lights