Smart data acquisition system for utilities metering

Abstract

The paper approaches the task of automatically reading and recognition of registered data on the utility meters of the users and is a part of a more complex project of our team concerning the remote data acquisition from industrial processes. A huge amount of utility meters in our country is of mechanical type without remote acquiring facilities and as an intermediate solution we propose an intelligent optical acquisition system which will store the read values in desktop and mobile devices. The main requirements of such a system are: portability, data reading accuracy, fast processing and energy independence. The paper analyses several solutions (including Artificial Neural Networks approach) tested by our team and present the experimental results and our conclusions.

The recognition of graphical patterns invariant to geometrical transformation of the models

“…These descriptors were used in reference 3 in comparison with Fourier descriptors for hand posture recognition and in references 1, 2 the same comparison is made in recognition of alphabet letters images. Hu proposed a set of orthogonal moment invariants, which can be used for scale, position, and rotation invariance computed from normalized moments η pq up to order three, with the following formulas 7 : (5) In order to compute the Hu's moments involved in the studied instances in our work we used the toolbox LISQ 2 , Version 1.3, December 21, 2006. The main objectives of the study were:…”

“…We are interested especially in recognizing digits independent of scaling, rotation or translation in the image because we addressed the problem of automate (optical) reading of the utility meters 5 . Figure 1 shows examples of meters images acquired and one can observe the need of a robust recognition system invariant to geometrical transformations of the digit to be recognized.…”