摘要
1 引言
对称性是物体与形状的基本特征之一,在图像分析和计算机视觉等领域是一个重要的研究课题.形状的对称性描述和物体对称性特征检测在机器人识别、检验、抓取和推理中有重要应用.根据物体的对称性,可以迅速确定物体内部相对位置关系,使被遮挡或丢失的部分信息恢复出来,并且还可以获得物体在三维空间的位置、方位和姿态[1].物体的对称性在图像压缩、形状匹配、目标识别和图像数据库检索等许多领域都有重要应用[2].
The symmetry detection of the object is important research area in image analysis and computer vision,and is usually applied in shape matching,model-based object matching,reconstruction of 3D objects,image compression,image database retrieval and so on. This paper defines some of the symmetries by using the representation of mathematics,summarizes the existing methods of symmetries detection by now,and compares their advantages and disadvantages. Furthermore, the paper suggests research directions on the symmetry detection based on the implicit polynomials.
出处
《计算机科学》
CSCD
北大核心
2001年第5期101-103,106,共4页
Computer Science
基金
国家自然科学基金(编号:69785003
69585002)
关键词
计算机视觉
平面图像
对称性检测
几何变换
Symmetry detection
Computer vision
Symmetric axis
Shape analysis