We have six teammates in our team. We mainly use the third-party Azure computer vision API from Microsoft, to build up a web application, which enables students can take snapshot of lecture slides, or even hand-written notes on the whiteboard. With the help of Azure computer vision API, we can use our mobile phones to read text in the images and translate them to text file and store them such files into cloud drive like Google drive. The front-end web interface is built with third-party API including Bootstrap, jQuery and HTML5 technology, while the back-end is built with API Django, Oauth2client, apiclient, httplib2, Google Drive & Apps Script APIs and Azure computer vision in Python programming language. An image gets uploaded to our web server, then to Google Drive, and then to Microsoft for image processing; after this process the text or result can be shared to various other platforms (document, email etc).

Share this project: