Project VISION for Visually Impaired or Blind Individuals

Votes: 19
Views: 1291

Life is really hard for the visually impaired or blind individuals, to the extent that they are unable to see what's happening around them, including reading books or understanding Morse code. However, there are solutions available to address this situation and potentially help them regain some level of vision. One such solution is Vision, an image processing device specifically designed for the visually impaired. Vision utilizes machine learning to recognize and audibly pronounce letters found on book pages.

Let's begin by explaining image processing. In simple terms, image processing involves the manipulation of electronic images captured by a camera or similar devices, converting them into a readable format on another device. This concept is commonly used in various applications, such as computers, phones, and similar devices that process images obtained from cameras. In the case of Vision, image processing is employed to handle the images of book pages captured by the device.

However, image processing alone cannot vocalize words effectively. To accomplish this, the system must have knowledge of the letter shapes and their corresponding pronunciation. This is where machine learning comes into play. Machine learning is a branch of artificial intelligence focused on developing systems that learn from data and improve their performance accordingly. To illustrate this, let's consider an artificial intelligence system that can differentiate between balls of different colors. Initially, the system needs to learn about colors and how they relate to the balls. This is achieved through supervised learning or similar machine learning techniques, where the AI system is trained to recognize colors and associate them with specific ball types. Similarly, on Vision, machine learning is employed by the artificial intelligence system to recognize letters.

On the Vision device, artificial intelligence processes the images captured by the camera. This process utilizes the Python programming language and the OpenCV library. OpenCV is a widely used image manipulation library that provides convenient methods for developers, supporting languages such as Python and C++. By utilizing OpenCV, the artificial intelligence on Vision distinguishes the letters on the book pages and produces corresponding sounds at specific frequencies through sound-emitting devices.

The goal of the Vision project, as previously mentioned, is to enable visually impaired or blind individuals to comprehend written text from books, walls, or any other surfaces.


Voting is closed!


  • Name:
    Dogus Yigit
  • Type of entry:
    Team members:
    • Ekin Deniz Cinar
    • Kaan Karaca
    • Selim Ocal
  • Patent status: