-
-
viewing page
-
Upload page
-
Home page
Inspiration
Improving literacy in minority and underrepresented groups. We all experienced first hand when reading to underrepresented students in high school the discrepancy between many students of minority communities and their classmates. Our project aims to help fight this problem.
What it does
ImLiterate lets students upload images of any text, and lets students learn about the definitions and pronunciations of all the words found in the image.
How we built it
We build ImLiterate with python, django, html, javascript, css, the Google Visions API, and the Merriam Webster API.
Challenges we ran into
One major challenege was extracting the dictionary data from the Merriam Webster api through javascript, as the api naming conventions interfered with data extraction. Another major challenge was taking the extracted word list from google vision and implementing it in our viewer page, but we solved this issue with forms and django paths.
Accomplishments that we're proud of
We are most proud of our program being able to handle all sorts of image files and image clarity. Even if the text is in cursive, our program is able to transcribe the file perfectly well. Another accomplishment we are proud of is being able to access the dictionary defintions of each individual word transcribed, along with the pronunciation of the word.
What we learned
We learned how to implement Django for a full stack web application. We learned how to utilize Google Cloud Vision and the Merriam Webster API.
What's next for ImLiterate
Next, we are going to improve upon the UI, since we focused on functionality over appearance for the hackathon. We are also going to host our project so anyone can access it.
Log in or sign up for Devpost to join the conversation.