基于局部二进制描述SIFT特征的锆石图像配准方法  

Zircon image matching method based on description of SIFT feature by LBP

作　　者：邱春玲[1] 陶强[1] 范润龙 王培智[1] 

机构地区：[1]吉林大学仪器科学与电气工程学院,长春130022 [2]中国地质科学院地质研究所,北京100037

出　　处：《吉林大学学报（工学版）》2014年第6期1793-1798,共6页Journal of Jilin University:Engineering and Technology Edition

基　　金：国家重大科学仪器开发专项项目(2011YQ050069;2011YQ05006907)

摘　　要：针对尺度不变特征变换(SIFT)算法计算复杂度高、匹配速度慢的问题,提出一种新的局部二进制模式(LBP)特征描述方法,描述SIFT算法检测出的锆石图像特征点,然后用主成分分析法(PCA)将生成的描述向量降维,最后利用欧式距离法完成配准。新LBP描述方法计算简单,具有旋转不变性和光照不变性,描述向量经过PCA降维以后匹配过程简单快速。实验结果表明:配准效果可以满足仪器自动寻样的需求,并且能够显著提升锆石图像的配准速度、提高仪器运行效率。In order to solve the problem of high computational complexity and low matching speed of the traditional Scale Invariant Feature Transform（SIFT）algorithm,a new method of feature description using Local Binary Patterns（LBPs）was proposed.This method was used to describe the zircon image feature points detected by SIFT algorithm.The dimensionality of the feature vector was reduced using Principal Component Analysis（PCA）,and the descriptor matching was carried out with Euclid Distance.The new description method of LBPs has a more simple calculation,and this algorithm has excellent features of rotation invariance and illumination invariance.The descriptor matching is faster after PCA dimension reduction.Experimental results show that this method meets the requirements of automated sample search,and significantly improves the matching speed of zircon images,improves the efficiency of the instrument.

关 键 词：计算机应用 图像配准 SIFT算法 局部二进制模式 主成分分析 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]