EyeGuide

Inspiration

According to the World Health Organization (WHO), over 2.2 billion people worldwide are visually impaired, highlighting a significant need for assistive technologies and inclusive services. Rapid technological advancements, including AI, offer opportunities to enhance accessibility, addressing the diverse needs of this demographic. By catering to the visually impaired, businesses can not only tap into a sizable market but also promote social inclusion and enhance global quality of life.

What it does

Eyeguide is a versatile app catering to visually impaired individuals and those requiring assistance with object recognition and organization. It employs image processing and text-to-speech technologies to offer real-time support in various scenarios.

The app features two main modes:

Walking Assistant: Utilizing the device's camera, Eyeguide monitors the user's surroundings, identifying potential hazards and providing verbal instructions in real-time to navigate safely.
Searching Assistant: Users can submit images and verbal cues to search for specific items. For instance, color-blind individuals can utilize the app to locate objects based on color, or users can find small items in cluttered environments efficiently.

How we built it

Eyeguide was developed using a combination of frontend and backend technologies. The frontend interface was created using JavaScript, HTML, and React, while the backend utilized Python, Flask, and the Gemini API. Adaptive video sampling was implemented based on conversation complexity to enhance user experience. The Gemini API's multimodal capabilities were instrumental in processing visual and verbal information.

Challenges we ran into

Integrating the Gemini API for image processing posed challenges, as did ensuring smooth interaction between the app's functionalities. Optimizing performance for real-time image processing and accurate text interpretation was also challenging.

Accomplishments that we're proud of

We take pride in delivering a comprehensive solution that caters to the needs of visually impaired individuals and offers assistance with object recognition and organization. The app's user-friendly interface and seamless integration of technologies make it a valuable tool for enhancing accessibility and independence.

What we learned

Developing Eyeguide taught us how to effectively utilize the Gemini API and leverage image processing and text-to-speech technologies to create accessible applications. We also gained valuable insights into the daily challenges faced by visually impaired individuals.