Rock Image Segmentation of Improved Semi-supervised SVM–FCM Algorithm Based on Chaos.

In the process of petroleum resource exploitation, porosity is the key parameter to evaluate reservoir fluid fluidity. Rock image segmentation is a challenging task due to the complex geological structure, unevenness, noise, etc. In order to solve the above problem, the improved semi-supervised SVM–FCM algorithm based on chaos (CSVM–FCM) is proposed to segment rock images in the paper. Firstly, the chaotic map is embedded into the PSO algorithm, then the improved PSO is used to find the optimal parameter configuration of the SVM model, and the binary initial segmentation of the rock image is realized. Finally, the semi-supervised FCM algorithm based on the objective function improvement is implemented to further segment the image, and segment the pores and rocks. In order to prove the superiority of the method, the method was compared with several other methods. The experimental results show that the method proposed in this paper has better segmentation effect, high precision and good performance. [ABSTRACT FROM AUTHOR]