分块多项式确定性矩阵SIFT图像配准算法  

An SIFT Image Registration Algorithm Based on Block Polynomial Deterministic Matrix

作　　者：卢健[1] 陈泽民 马成贤 何金鑫 LU Jian;CHEN Ze-min;MA Cheng-xian;HE Jin-xin(School of Electronic and Information,Xi'an Polytechnic University,Xi'an 7I0048,China)

机构地区：[1]西安工程大学电子信息学院,西安710048

出　　处：《电光与控制》2019年第1期12-16,共5页Electronics Optics & Control

基　　金：国家自然科学基金(61040055);陕西省教育厅专项科学研究计划项目(17JK0332);陕西省科技厅科技发展计划项目(2011K06-01);西安市碑林区应用技术研发项目(GX1807)

摘　　要：针对尺度不变特征变换(SIFT)算法在关键点(即尺度空间稳定的极值点)特征描述向量计算复杂且维数较高,以及多项式确定性矩阵测量数取值受限等现象,提出一种分块多项式确定性矩阵的SIFT图像配准算法。通过压缩感知的稀疏表示方法,将SIFT提取的高维描述子向量降维到低维的稀疏特征向量,降低了关键点描述向量维度,并采取欧氏距离对图像关键点特征描述向量进行相似性度量。与传统算法的针对性比对分析表明,改进算法有效提升了配准精度,增强了实时性。For the Scale-Invariant Feature Transform( SIFT) algorithm the eigenvectors at the key points( the extreme points of a stable scale space) are computationally complex and usually have high dimensionswhile the values of the polynomial deterministic matrix are limited. To solve the problems an SIFT image registration algorithm based on the block polynomial deterministic matrix is proposed. The SVM-derived sparse representation method is used to reduce the high-dimensional descriptor vector extracted by SIFT to a low-dimensional sparse feature vector which reduces the dimensions of key-point description vector. The Euclidean distance is used for similarity measurement of the key-point feature description vector. The contrastive analysis with the traditional algorithms shows that the improved algorithm can effectively improve the registration accuracy and enhance the real-time performance.

关 键 词：图像配准 SIFT 分块多项式确定性矩阵 压缩感知 

分 类 号：TN919.8[电子电信—通信与信息系统]