Electric power facility normalization judgment system based on machine learning and edge detection

• Main Authors: CHEN MING, WANG YUNAN, LAN SENLIN, QIN HONG, MAO DILIN, MA YUAN, SHEN JIAYI, CAO XIU, HE HUIZHI, JI CHENGYUE
• Format: Patent
• Language: Chinese; English
• Published: 17.06.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses an electric power facility normalization judgment system based on machine learning and edge detection. The electric power facility normalization judgment system comprises the following steps: step 1, extracting key components in a meter box photo by using a yolk target detection algorithm in machine learning; step 2, carrying out image processing on the extracted key component, and finding out edge structure features of the key component, including a frame, an edge length and a bounding box area; and step 3, calculating the distance and the inclination angle of the target according to the edge structure characteristics to judge whether the target meets the installation specification. A target detection technology and an edge detection technology in machine learning are combined, a to-be-recognized object in an image is positioned through target detection, a target image with an image background removed is cut, contour features of the cut image are extracted by means of an edge detectio