The VisionX

VisionX aids visually impaired, dyslexic users by scanning text and surroundings, providing audio descriptions. It supports multiple languages, connects to Bluetooth, and features a wide-angle camera.

Comment

The VisionX Project

Written without a drop of AI, looks so only due to formatting.

What it does

VisionX is a portable device to assist individuals with visual impairments, autism, and dyslexia. It uses AI to analyze images and provide real-time audio descriptions of the content. For example, it can scan text from books, newspapers, or signs and read it aloud to the user. It can also describe objects in the user's environment, helping them navigate and understand their surroundings.

How we built it

Hardware:

  • Raspberry Pi: The central processing unit of the device, running the software and controlling the camera.
  • PiCamera Module: Captures images of the text or objects.
  • Button: Triggers the image capture and audio output.
  • Power Source: A rechargeable battery pack to power the device.

Software:

  • Python programming language was used to control the Raspberry Pi and interact with the AI.
  • The project utilizes an AI model (like the one from Gemini) to analyze images and generate descriptive text.

3D Design:

  • The device's enclosure was designed using Tinkercad, a 3D modeling software.
  • The design focuses on the protection of the internal components.
  • The 3D-printed case houses all the hardware safely.

Challenges we ran into

  • AI Accuracy: Ensuring the AI model consistently provided accurate and informative descriptions was a significant challenge.
  • Image Processing: Optimizing the camera and image processing algorithms to handle various lighting conditions and text sizes was crucial.
  • Size of Power Source: On the day of the STEAM day event, we realized the power source was too big to fit all the other components, so we had to shred some of the wires to make space.

Accomplishments that we're proud of

  • Successfully developing a functional prototype that meets the core objectives of assisting individuals with visual impairments.
  • Mastering the use of the Raspberry Pi and Python for hardware and software development.
  • Designing and 3D-printing a custom enclosure for the device.
  • Integrating AI technology into a real-world application with a positive social impact.
  • Learning about the challenges and considerations involved in developing assistive technologies.

What we learned

  • Technical Skills: Python programming, hardware interfacing, 3D modeling and printing, AI integration.
  • Project Management: Teamwork, time management, problem-solving, and iterative development.
  • Interdisciplinary Collaboration: Working effectively with team members possessing different skills and expertise.
  • Importance of User-Centered Design: Considering the needs and perspectives of the target users throughout the design and development process.
  • Social Impact of Technology: Understanding the potential of technology to address real-world challenges and improve people's lives.

What's next for The VisionX

  • Miniaturization: Reducing the size and weight of the device for improved portability and ease of use.
  • Enhanced AI Capabilities: Integrating more advanced AI models for improved accuracy, multilingual support, and real-time video processing.
  • User Interface Enhancements: Developing a more intuitive user interface, potentially with voice control options.
  • Expanding Use Cases: Exploring applications beyond text reading, such as object recognition, scene understanding, and navigation assistance.
  • User Testing and Feedback: Conducting extensive user testing to gather feedback and refine the device based on user needs and preferences.

Built With

  • API
  • CMD
  • Gemini
  • Python
  • Raspberry Pi
  • Terminal

Built With

Share this project:

Updates