Magnetite microscopic image segmentation method based on semantic segmentation

• Main Authors: LIANG XIUMAN, WU JIAHUI, NIU FUSHENG, XUE WENQIANG, ZHANG JINXIA, ZHANG HONGMEI, YAO SHANSHAN
• Format: Patent
• Language: Chinese; English
• Published: 04.01.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention belongs to the technical field of mineral engineering, and particularly relates to a magnetite microscopic image segmentation method based on semantic segmentation. The method comprises the following steps: acquiring a plurality of magnetite microscopic images of a metasomatic relict texture; segmenting the magnetite microscopic image into a deep color area and a light color area by adopting a semantic segmentation network; performing image enhancement on the segmented microscopic image to obtain a target mineral microscopic image; and inputting the target mineral microscopic image into a preset mineral classification network model to obtain gangue and mineral particle images obtained after image segmentation. Compared with other U-shaped networks, the U-shaped network which is based on a feature multiplexing structure and a coding and decoding structure and is capable of aggregating the features of multiple stages is adopted, and in a trained preset mineral microscopic image segmentation model,