基于概率神经网络的岩石薄片图像分类识别研究  

Rock Image Classification Recognition Based on Probabilistic Neural Networks

作　　者：程国建[1] 杨静[1] 黄全舟[1] 刘烨[1] 

机构地区：[1]西安石油大学计算机学院,西安710065

出　　处：《科学技术与工程》2013年第31期9231-9235,共5页Science Technology and Engineering

基　　金：国家自然科学基金(40872087)资助

摘　　要：为实现岩石薄片图像孔隙识别的自动化,提出了一种基于聚类分割和神经网络相结合的分类识别方法。首先在图像中应用Kmeans聚类分割算法,将岩石图像分割为背景岩石和目标孔隙两类,并分别提取足够特征进行分类测试,效果良好。其次选100幅岩石图像,每组5幅图像共20组,每组200个数据进行验证。实验表明,建立好的概率神经网络可以准确分类识别出目标孔隙,识别平均正确率为95.12%,已达到实际应用需要。In order to realize the recognition automation of rock section pore images, a method combined Kmeans clustering with probabilistic neural network is proposed and applied to rock section images. Firstly, Kmeans cluste- ring is used as segmentation algorithm, the rock images are divided into two types and extracted enough features and it is shown good classification effect on testing dataset. Secondly, 100 pieces of rock image section are used as vali- dation dataset, including 5 images of each 20 groups, a group has 200 data samplings. Experiments show that the probabilistic neural network can be used as rock texture classifier, the average correct classification rate is around 95.12%, which can meet the practical application needs.

关 键 词：Kmeans聚类 概率神经网络 岩石薄片图像 模式识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]