A Novel Hybrid Canny, Sobel, Robert, and Prewitt Algorithm for Enhanced Schematic Edge Detection in Power Distribution Networks

Power distribution networks are crucial for the efficient delivery of electricity, and precise schematic interpretation is vital for maintenance, troubleshooting, and making operational decisions. However, the complexity of these schematics presents challenges in edge detection, which is critical for enhancing clarity and interpretability. This paper presents a new hybrid edge detection algorithm, created by the authors, which combines the Canny, Sobel, Robert, and Prewitt algorithms. The proposed hybrid algorithm seeks to overcome the limitations of individual edge detection methods by utilizing their combined strengths. Performance assessments were carried out on 178 schematic datasets, utilizing key metrics such as True Positive Rate (TPR), False Positive Rate (FPR), and Accuracy (ACC). The results show that the proposed hybrid algorithm attains a TPR of 0.7482, an FPR of 0.0409, and an ACC of 0.9493, surpassing traditional methods in balancing sensitivity, specificity, and accuracy. The robustness and reliability of this hybrid approach make it a promising solution for edge detection in complex power distribution network schematics. Future research will focus on optimizing the algorithm to further reduce FPR and exploring the integration of machine learning techniques to enhance adaptability across diverse network configurations.