基于采样点组二值化策略的鲁棒二值描述子研究  

Sample Point Group Based Binary Method for Robust Binary Descriptor

作　　者：刘红敏[1] 李璐 王志衡[1] LIU Hong-min;LI Lu;WANG Zhi-heng(School of Computer Science and Technology,Henan Polytechnic University,]iaozuo 454000,China)

机构地区：[1]河南理工大学计算机科学与技术学院,焦作454000

出　　处：《计算机科学》2017年第12期292-297,309,共7页Computer Science

基　　金：国家自然科学基金(61472119;61572173;61472373;61401150);计算机视觉与图像处理创新团队(T2014-3);河南理工大学杰出青年基金项目:基于二值特征描述子的图像匹配方法研究(J2016-3)资助

摘　　要：鉴于当前基于采样模型的二值描述子的采样信息相关度高且描述子的鲁棒性较低,通过改进视网膜采样模型,提出基于采样点组二值化策略的鲁棒二值描述子。首先,通过减少采样层数并增大采样点间的距离,设计出低采样点密度和低采样区域重叠度的改进视网膜采样模型。然后,在模型中的采样点圆形邻域内获取若干像素点,将其与采样点一起组成采样点组,分别计算两个采样点组对应点的灰度对比结果,并利用投票策略决定最终二值结果。最后,将采样点组的梯度对比信息与灰度对比信息一起编码生成描述子,以提高对相似灰度区域的描述力。通过对比实验可以看出,所提二值描述子对各种图像变化具有较好的鲁棒性且具有较好的匹配效果。Since a binary descriptor with a sampling pattern usually extracts information with high correlation and behaves less robust,through improving the retina sampling pattern,this paper proposed a novel sampling point group based binaryzation strategy to generate descriptor.Firstly,by reducing the number of sampling layers and enlarging the distance between sample points,an improved retina sampling pattern with low sampling density and low overlapping between sampling fields is designed.Then a sample point group is constructed by extracting some points surrounding a sample point in the pattern.Next,the binary result of a pair of sample point group is determined by voting their corresponding points’intensity tests.Finally,the image gradient information is also computed and added to the final descriptor so as to enhance descriptor's description power.Experiment results reveal that the proposed descriptor is robust to various image transformations and outperforms the four compared descriptors.

关 键 词：特征匹配 采样模型 二值描述子 采样点组 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]