Neural Data Processing in Scanner of Static Elements

Abstract

This article presents the design and the subsequent implementation stages for the low-cost shape scanner of relatively small elements. The main concept of hardware and data processing algorithm are described. The code used for controlling the operation of individual parts of the device was implemented in the Arduino platform. Special software for managing work of the scanner and collecting measurement data was prepared using the Processing programming language. Assuming cost reduction and simple device construction, limited precision of the shape scanning is expected. In order to improve the obtained results, reduce the disturbances and increase the resolution (the number of points describing shape), additional data conversions performed using the neural network were used.