Implementation of Moment Invariant in Recognizing of Electrical Meter Numbers

Abstract

Implementation of computer vision can be done in the introduction of images or pictures of characters of numbers or letters. Based on this, then the computer vision can be used in the introduction of numbers on the electric meter or commonly called kWh meter. The underlying thing for the electric meter to be the object of research is to look at the situation, where the electric meter recorder keeps the record using the camera. Furthermore, the value shown on the electric meter will be inputted manually. Manual input requires a relatively long time because the amount of electricity meter input value is not small data. One method that can be used in recognizing the shape of the image in computer vision is the invariant moment. The results of this study indicate that the quality of the image gives effect, both in terms of the extraction of features and the accuracy of the recognition of the figure on the image of the electric meter. In addition to this, the threshold value of the euclidian distance method should also be used to limit the recognition process.

Personality Type Analysis through Handwriting Characteristics Mapping using Invariant Moment Descriptors

“…This improvement may be attributed to the fact that the invariant moment value is unaffected by potential transformations during the pre-processing stage. This notion is supported by research conducted by Syafie et al [24] in recognizing numeric data on electricity meters through a blurring process, as well as by Narudin et al's research [25] in analyzing transformed images. As a result, the accuracy obtained in this study reached 85.7%.…”