Inspiration

Recently, one team member had been a bit hasty and deleted the his code for a project. Left with only a couple of screenshots that he had taken for documentary purposes, he was forced to go back and slowly type out what was in the images. This problem inspired the team to make a website that would help recognize the text in images automatically, making the process faster and more accurate.

What it does

Our website, imatex.tech, takes in as input the url of an image. It will then take this url and contact an API which will help it parse the image for text. The results are outputted onto the website, where the user can easily copy and paste them.

How we built it

We used HTML, CSS, and JavaScript to create the website, as well as Bootstrap for help with the front-end part. Node.js and Axios were also used for the back-end, while Github was what we used to collaborate on the code and manage the versions. Domain.com was used to buy the domain.

Challenges we ran into

Formatting with CSS was a challenge, as well as finding a way to make the website visually pleasing.

Accomplishments that we're proud of

Getting the CSS to do what we want, using Node.js and Axios, as well as effectively working with an image-recognition API.

What we learned

How to use Node.js and Axios, also more in-depth features, uses, and behaviours of CSS and Bootstrap.

What's next for ImaTex

Adding extra functionality, mainly with letting the user submit more image types. Mark-up features are also being researched.

Share this project:

Updates