RBFD 一种鲁棒的图像局部二值特征描述子.pdf

第27 卷 第 5 期 计算机辅助设计与图形学学报 Vol. 27 No. 5 2015 年5 月 Journal of Computer-Aided Design & Computer Graphics May 2015 RBFD: 一种鲁棒的图像局部二值特征描述子 1, 2) 3) 1, 4) 1, 4) 1, 4)* 耿利川 , 成 运 , 苏松志 , 林贤明 , 李绍滋 1) (厦门大学信息科学与技术学院 厦门 361005) 2) (许昌学院城乡规划与园林学院 许昌 461000) 3) (湖南人文科技学院通信与控制工程系 娄底 417000) 4) (福建省仿脑智能系统重点实验室(厦门大学) 厦门 361005) (szlig@xmu.edu.cn) : 针对传统浮点型特征描述子占用空间大、匹配速度慢的问题, 提出一种基于梯度统计信息比较的局部二值 特征描述子. 通过对比特征点邻域梯度统计信息生成二值特征描述子, 再利用多邻域和多分块策略提高描述子判别 力, 最后通过近似简化的 AdaBoost 算法实现描述子降维. 实验结果表明, 与已有描述子相比, 文中提出的描述子在 实现快速生成的同时其鲁棒性更强. : 局部特征; 二值特征描述子; 图像匹配 : TP391 RBFD: a Robust Image Local Binary Feature Descriptor Geng Lichuan1, 2), Cheng Yun3), Su Songzhi1, 4), Lin Xianming1, 4) , and Li Shaozi1, 4)* 1) (School of Information Science and Technology, Xiamen University , Xiamen 361005) 2) (School of Urban Planning & Landscaping, Xuchang University, Xuchang 461000) 3) (Department of Communication and Control Engineering, Hunan University of Humanities , Science and Technology, Loudi 417000) 4) (Fujian Key Laboratory of the Brain-like Intelligent Systems (Xiamen University ), Xiamen 361005) Abstract: The traditional floating feature descriptors are in high memory load and slow in matching. To best address these problems, this paper proposed a novel binary feature descriptor based on gradient statistic information comparison. Firstly, the image patch around the keypoint is divided into sub-regions, and our binary descriptor is constructed by comparing the gradient statistic information of these sub-regions. Then, a multi-gridding and multi-support region strategy is applied to boost the dis