Basically my project device will detect an object. Then it will help visual impairment by voicing it out what the object is. Figure below shows the flow diagram of the expected prototype design will be.
Figure 1: Flow diagram of the prototype design.
According to the diagram, the input is from the capture of real time video by the camera. Then it will process by the object detection algorithm and deep neural network processing unit until the object detected and identified. The last step is the output, which it will voice out through the speaker according to the text speech processing unit.