Vision Crafters

What it does

Aim:
Our mobile app empowers visually impaired individuals by enhancing their understanding of surroundings. Using the device's camera, the app captures images or videos and processes them via the Gemini API to generate descriptive text, which is then converted to speech. The app also features gesture controls for photo/video capture and integrates hazard detection to raise alarms in dangerous situations.

Gemini Integration:
Gemini is integral to our app, delivering advanced scene-to-text processing capabilities. It translates visual data from images and videos into accurate, detailed textual descriptions. Gemini excels at recognising complex scenes and identifying potential hazards, providing users with precise and actionable feedback. This functionality is crucial for creating an accessible and informative experience, making Gemini essential for both text descriptions and hazard detection. Additionally, Gemini is used to generate titles for interaction logs.

Features:
-Scene-to-text processing with Gemini.
-Text-to-speech, speech-to-text, and Gesture controls for accessibility.
-Hazard detection with Gemini and alerts.
-Interaction logs with Gemini-generated titles.

End Users:
Designed for visually impaired individuals and their caregivers.

Benefits:
-Enhanced understanding of surroundings through audio.
-Improved safety with hazard alerts.
-Increased independence and easy access to logs.