fbpx

One of our greatest desires is to see that every blind person has independent access to visual/spatial content. We know this might sound like fiction, but it’s not. Blind people can enjoy visual content though tactile drawings, but only with the help of another person. That person must guide their hands on the drawing while giving spoken information about it. 

 

This 1:1 education slows down the learning process considerably, which means that the blind are dependent on others if they want to enjoy tactile drawings. Now, this is where the READER App comes into the picture – it’s here to become the person over the shoulder and give the blind the independence they need. This is possible with the aid of modern technologies such as Machine Learning and Image Recognition. 

 

  1. The Human Eye VS Image Recognition and Machine Learning
  2. The Tactile Images READER Mobile App

a) Reading a tactile drawing 

b) Further development

1. The Human Eye VS Image Recognition and Machine Learning

 

Source: v2osk | Unsplash 

Let’s take the image of a cat. People see it, without any special effort, without even being aware of the fact that the process of seeing has taken place. That’s because they have the advantage of a couple of million years of evolutionary context that helps them determine what it is. 

 

Computers, on the other hand, do not have this advantage. And neither do the blind. But with modern means, computers can be given this advantage to help the blind. What computers do see is data. So, if we give computers enough data and train that information to make them understand what the numbers represent, a computer can identify that specific data. And this training is done through Machine Learning. 

 

Computer vision works by breaking an image down into smaller groups of pixels. Then, a series of calculations are made to compare them to specific patterns. 

 

For a computer to see the image of a cat just like the human eye does, the algorithms need to process a lot of images of a cat, from a multitude of angles. This database would come to replace humans’ countless years of evolution and their capacity to contextualize.

2. The Tactile Images READER Mobile App 

a) Reading a tactile drawing

The Tactile Images READER Mobile App is the virtual assistant of a visually impaired person. It is a companion app because it follows the blind wherever they go. The App can read tactile drawings with the aid of Machine Learning and Image Recognition. 

 

Because of Image Recognition, operating with tactile drawings is very easy. Meaning your phone does not have to ”see” the entire drawing to be able to give information. The closest you get to the drawing, the easier it is for the App to recognize the zoomed-in parts of the image. 

 

”Areas of Interest” give audio information as a person reaches that area with his/her finger. The process goes like this: when a person reaches an area of interest, the mobile App beeps once, and if the person stays on the area for a couple of seconds, the App beeps three times. Then, the App gives audio information. In this way, the blind can study visuals independently. Once the person moves his/her finger away from the area of interest, the audio description stops.

b) Further development

The Tactile Images READER App is now in Alpha testing and available only for iOS. You can download it from the App Store free of charge. But our dream is to make the App available for Android as well. In this way, we could reach all the blind people, their families, and the teachers for the blind who own with a smartphone. If you believe in our dream, you can help us accomplish it by donating.

It’s time for the blind to enjoy the benefits of individual study! The READER App is here to replace the person over the shoulder, the specialist who gives information and guides their hands on the tactile drawing. Download free tactile drawings from the App LIBRARY, emboss them manually, and start exploring! 

Do you have any questions about the Mobile READER App? Write in the comment section below! 

0 Comments

Submit a Comment

Your email address will not be published. Required fields are marked *