Schematic Edge Detection of Power Distribution Networks Using the Canny, Sobel, Robert, and Prewitt Algorithms

• Published in: 2023 IEEE International Conference on Computing, ICOCO 2023
• Main Author: Rahman A.Y.; Zakaria Z.
• Format: Conference paper
• Language: English
• Published: Institute of Electrical and Electronics Engineers Inc. 2023
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85184856196&doi=10.1109%2fICOCO59262.2023.10397989&partnerID=40&md5=433c634b975ac43055909848f0293fcc

Electrical power distribution network schemes are often seen in electrical network learning manuals. Understanding these schemes is crucial for learning. However, schematic drawings of these networks can be unclear or difficult to interpret, leading to misunderstandings among learners. To address this issue, a detection system for power distribution network schemes using four algorithms, i.e., Canny, Sobel, Robert, and Prewitt, is proposed. From testing the 5 resulting schematic image data, it is found that Robert's Algorithm had the highest true positive rate (TPR) value of 0.823, indicating its effectiveness in edge detection. Meanwhile, the Canny algorithm had the lowest false positive rate and highest accuracy of 0.941, making it a suitable choice for both edge and non-edge detection. Therefore, the Canny algorithm can be recommended for learners to understand the electric power distribution network scheme better. © 2023 IEEE.