This project is an attempt in this direction to build a novel smart glass which has the ability to extract, recognize and translate text captured from an image and convert it to speech.
This project is an attempt in this direction to build a novel smart glass which has the ability to extract, recognize and translate text captured from an image and convert it to speech.
The problem Text Translation Glasses solves
Looking around and we stumbled upon the fact that the visually challenged are so dependent on others for their daily chores. Even for a small task as trivial as reading newspaper, they have to suffer a lot because of their infirmness. So we aim to devise a solution by building text detection glasses which will convert any text to speech making their life much easier and independent.
**Secondly the glasses are also capable to translate a language to any other language hence making it a good language translator, as we travel to different nations it is harder to communicate with others due to language barrier. **
It can be also used in navigation and language processing of various Bots and Drones once built by integrating the technology in them.
Challenges we ran into
Training a NLP Model is time consuming and getting the required accuracy is quite difficult.
Well to be honest the model crashed twice which takes 6 hours to complete.
We have to use various OpenCV Filters to remove noise from the captured image.