Download Project Document/Synopsis
Every year, the number of visually challenged persons is increasing due to eye diseases, age-related causes, traffic accidents and other causes. As reading is one of major importance in the daily routine (text being present everywhere from newspapers, commercial products, signboards, digital screens etc.) of humankind, visually impaired people face many difficulties.
We have developed our Android TTS OCR Converter System by keeping people with visual disabilities in mind. Our project can help a visually challenged person get information about the printed text, text boards, scene text, hoardings, and instructions on traffic signboards in audio form. The application is designed as a camera-based reading system that extracts text from an image and identifies the text characters and strings from the captured image and finally, the text will be converted into audio.
The system will auto-capture a photo. It will then process the photo using OCR (Optical Character Recognition). Here, we have used the Google Cloud Vision API for OCR. The system will then detect the text on the image and convert the text into speech. It will read out the text aloud.
The user can also use the volume button to operate the system. If the user turns down the volume once, the system will read the text again. If they turn down the volume twice, the system will capture another photo. If they turn the volume up, the system will exit itself.
In this project, the front end involves XML. The programming language is JAVA and the IDE used is Android Studio.
Advantages
- The system is easy to maintain.
- It is user-friendly.
- Very useful for visually challenged people.
- The system will detect the text on an image and convert it into speech.
- The volume button features help the user navigate the system efficiently.