❤️Inspiration:
Our inspiration for building this web app was to provide a simple tool for users to convert images containing text into editable text format.
What it does?
Our web app uses the Tesseract.js library to extract text from images uploaded by the user. The app then displays the extracted text in a text area, which the user can then copy and paste or save as a text file.
How we built it:
We built the web app using HTML, CSS, and JavaScript, with the Tesseract.js library being used for the image-to-text conversion. We also used some additional libraries such as jQuery and Bootstrap to enhance the user interface and experience.
Challenges we ran into:
One of the main challenges we faced was fine-tuning the Tesseract.js library to accurately extract text from images, as it sometimes struggled with certain types of fonts or images with low contrast. We also faced some design and layout issues during development, which required us to iterate on the design.
What's next🤔?
We will make an advanced version of this by making our own model and tuning it. This would involve training our own machine learning model for text recognition, which we can then integrate into the web app. This would potentially improve the accuracy of the text extraction, particularly for more challenging images.
