Overview / Usage

In recent times, there have been many products that cater to the visually challenged, but only few have been readily available for regular use. The reason being, that the technology driving these products are costly, or complex to use. In this work, we propose a “Vision system with audio feedback to assist visually impaired to grasp objects”. Our proposed system eliminates these challenges, in its usability, complexity and functionality. The system is designed to serve the following: (1) Finding a desired object in the scene, in which, the object recognition is done using Weighted Matrix Algorithm from the visual input received from the camera; and (2) Assisting the user to the object’s proximity, where, the user is guided using audio-feedback, at every step. This approach is represented taking the example of a commonly found object in our household. We have considered a water bottle. The above approach is found to produce suitable results.

Methodology / Approach

The system is designed to serve the following:
1 Finding a desired object in the scene, in which, the object recognition is done using Weighted Matrix Algorithm from the visual input received from the camera
2 Assisting the user to the object’s proximity, where, the user is guided using audio-feedback, at every step. This approach is represented taking the example of a commonly found object in our household.

We have considered a water bottle. The above approach is found to produce suitable results.

Technologies Used

Rasberry pi 3,
Python
OpenCV

Other links

• paper Link