Help people with no access to education, educate themselves.
What it does
Identifies the objects shown to it, counts the number of objects and spells them out. This helps the illiterate person learn how to count, identify and learn the alphabet through spellings.
Displays a series of images of alphabets on screen and asks the person to identify it. Also tells whether the identification is correct or not.
Speaks an alphabet for the user to write it on the paper, captures the image of the alphabet and checks whether it matches with the asked alphabet or not.
Helps the person to read a book by taking in the image of the captured page of the book and reading it aloud.
How I built it
The front end was entirely made using pySimpleGUI. YOLO was used as object detection system. Pyttsx3 was used for text to audio and google sound API was used for audio to text.
Challenges I ran into
This was my first time working with pysimplegui. Designing multiple windows through master slave architecture was a challenge. Apart from that getting speech to text conversion API work was also a tough task as the application crashed everytime it was used but the issue was solved at the end.
Accomplishments that I'm proud of
I am proud of bringing my idea to life in a given period of time and experimenting with new technologies.
What's next for Self Tutor
Support for other languages can be added Other interactive teaching methodologies can be added.