计算机应用研究2016，Vol.33Issue(12)：3868-3871,4.DOI:10.3969/j.issn.1001-3695.2016.12.077
基于空间纹理相似性的图像角点特征匹配算法
Image corner matching algorithm using similarity of spatial texture
邵春艳 1丁庆海 2罗海波3
作者信息
- 1. 中国科学院沈阳自动化研究所，沈阳 110016
- 2. 中国科学院大学，北京 100049
- 3. 中国科学院光电信息处理重点实验室，沈阳 110016
- 折叠
摘要
Abstract
This paper proposed a novel image corner matching algorithm using the similarity of spatial texture aiming at ad-dressing the low matching rate and long computational time of traditional image corner matching algorithms.First,the algorithm calculated the spatial distance matrix of the corners in the image objects.Second,it transformed the measure of the image cor-ners into the measure of spatial texture amplitudes by calculating the Rayleigh quotient of the spatial distance matrix in the LBP feature space.Finally,it matched the image corners between different images by comparing their corresponding Rayleigh quo-tients.This paper carried out the corner matching between different images captured under different circumstances.The experi-mental results demonstrate that the proposed image feature matching algorithm is robust on the image transformation and pro-duces higher matching rate with less computational time.Compared with the-stated-of-art corner matching algorithm,the compu-tational time is decreased by 48 ms and 2408 ms when the calculated features numbers are low and high respectively.关键词
图像角点特征匹配/LBP特征向量/瑞利商/纹理特征空间Key words
image corner matching/LBP feature/Rayleigh quotient/spatial texture分类
信息技术与安全科学引用本文复制引用
邵春艳,丁庆海,罗海波..基于空间纹理相似性的图像角点特征匹配算法[J].计算机应用研究,2016,33(12):3868-3871,4.
