基于改进的SLIC的岩心颗粒图像边缘分割算法  

Particle edge segmentation algorithm of core image based on improved SLIC

作　　者：董领 卿粼波[1] 何小海[1] 黄帅坤 何海波 DONG Ling;QING Linbo;HE Xiaohai;HUANG Shuaikun;HE Haibo(College of Electronics and Information Engineering,Sichuan University,Chengdu 610065,China;Chengdu Xitu Technology Co.,Ltd.,Chengdu 610065,China)

机构地区：[1]四川大学电子信息学院,成都610065 [2]成都西图科技有限公司,成都610065

出　　处：《智能计算机与应用》2021年第9期54-58,共5页Intelligent Computer and Applications

摘　　要：在岩心颗粒图像进行目标提取的过程中,由于颗粒颜色丰富,类别和大小不一,且存在边界模糊等情况,导致颗粒分割很困难。针对以上问题,本文提出一种基于改进的简单线性迭代聚类(SLIC)算法,首先对图像进行预处理,增强目标区域同时模糊背景部分,消除孤立的噪声点且保护边缘信息;其次,结合LBP纹理特征对图像进行超像素分割;最后,结合区域之间的颜色特征进行超像素合并。实验表明,与现有的其它算法相比,该算法能准确地分割颗粒的边界,更有效地提取目标颗粒,极大地降低了后续对提取目标进行分析的复杂度。In the process of particle extraction from core image,it is difficult to segment the particles because of the rich color,different types and sizes of particles and fuzzy boundary. To solve these problems,an improved simple linear iterative clustering(SLIC)algorithm is proposed. Firstly,median filtering is used to eliminate the isolated noise points and preserve the edge information. Secondly,the image is segmented by super-pixel combined with LBP texture features. Finally,the super-pixel is merged by combining the color features between regions. Experiments show that the algorithm can segment the boundary of particles accurately,extract the target particles more effectively,and greatly reduce the complexity of subsequent image processing.

关 键 词：岩心颗粒图像 超像素分割 SLIC 超像素合并 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]