WANG Y M, HUANG L L, HOU G S ,et al.Combined segmentation of rock slice images under different polarizing systems[J].Journal of Henan Polytechnic University(Natural Science) ,2023,42(6):69-75.

doi:10.16186/j.cnki.1673-9787.2021090013

Received:2021/09/03

Revised:2021/10/20

Published:2023/11/25

Combined segmentation of rock slice images under different polarizing systems

WANG Yongmao1, HUANG Lingling1, HOU Guangshun2, LU Bibo1

1.School of Computer Science and Technology，Henan Polytechnic University，Jiaozuo  454000，Henan，China;2.School of Resources & Environment，Henan Polytechnic University，Jiaozuo  454000，Henan，China

Abstract:To solve the problem of low accuracy and time-consuming in the traditional switching between single polarization and orthogonal polarization systems for the analysis of rock slices and content estimation under microscope，a combined segmentation method of rock slice image in chrominance luminance space was designed.Firstly，the single polarized image and the orthogonal polarized image from the same field of view were decomposed separately in the chromatic and bright space.Then，the chromaticity image was subjected to bilateral filtering to suppress noise and remove texture.The difference between the filtered two chromaticity images was calculated，and the final segmentation result was obtained by using K-Means clustering algorithm and watershed segmentation algorithm in sequence.The research results can provide guidance for geologists to identify rock slices.

Key words:polarized systems;chromatic and bright space;bilateral filter;visually significant;K-Means algorithm

009_2021090013_王永茂_L.pdf