Image segmentation is an important basis for extracting the structure characteristics of the rock. In order to solve the problem that the traditional image segmentation method does not segment the rock image accurately, the genetic algorithm is used to optimize the traditional back propagation (abbreviated as BP) neural network image segmentation method. The features of the rock image domain are extracted, and the training samples are further corrected. Using the improved back propagation neural network rock image segmentation method, the rock image is segmented for three aspects: connected domain, local domain and edge domain. The calculation results compared with ImageJ software and traditional BP neural network show that under the condition of small sample size, the improved BP neural network not only can autonomously learn the whole connected structure, local domain structure and edge structure in the rock image, but improve the accuracy and speed of the BP neural network for rock image segmentation.

This content is only available via PDF.
You can access this article if you purchase or spend a download.