圆周二进制描述符的图像点特征提取方法-计算机辅助设计与图形学学报.pdfVIP

第29 卷 第 8 期 计算机辅助设计与图形学学报 Vol. 29 No.8 2017 年8 月 Journal of Computer-Aided Design Computer Graphics Aug. 2017 圆周二进制描述符的图像点特征提取方法 1,2) 1) 张 展 , 杨东升 1) ( 中国科学院沈阳计算技术研究所智能控制与装备实验室 沈阳 110168) 2) ( 中国科学院大学 北京 100049) (1184373364@) : 特征点描述符在特征提取、图像识别与定位中有重要作用. 针对 SIFT 等梯度方向描述符计算量大, ORB 等 二进制描述符匹配镜像图像入围率低, 提出一种圆周二进制描述符(CBD) 的图像点特征提取方法. 首先以 1:1.2 的比 例建立图像金字塔, 对每层图像进行高斯平滑, 使用FAST 检测特征点; 然后提出二值图像重心法计算特征点的方向, 以提升计算特征点方向的速率; 最后提出 CBD 图像点特征提取算法, 有效地解决了镜像图像匹配的问题. 实验结果 证明, CBD 具有良好的镜像不变性, 且适应性强、入围率高. ：图像识别; 圆周二进制描述符; 图像重心; 镜像不变性; 特征匹配 ：TP391.41 Image Point Feature Extraction Algorithm of Circumferential Binary Descriptor Zhang Zhan1,2) and Yang Dongsheng1) 1) (Intelligent Control and Equipment Laboratory , Shenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang 110168) 2) ( University of Chinese Academy of Sciences, Beijing 100049) Abstract: Feature point descriptors play an important role in feature extracting, image recognition and de- tection. For the large computation of gradient direction histogram descriptors such as SIFT etc. and the bi- nary descriptors’ defect that could not match the mirrored image very well such as ORB etc., an image point feature extraction algorithm of circumferential binary descriptor (CBD) is proposed. First, set up the image pyramid by the 1:1.2 ratio, Gaussian blur each image layer, detect the feature points with FAST detector. Then, the binary image’s centroid algorithm is given to compute the orientation of the feature points. With this method the computation speed is improved. Last, CBD is proposed to solve the problem that the other descriptors couldn’t match mirrored image