Shape similarity retrieval under affine transforms
Shape similarity retrieval under affine transforms
复制标题
DOI：
10.1016/s0031-3203(01)00040-1
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
F. Mokhtarian;Sadegh Abbasi
中科院分区：
文献类型：
--
作者：
F. Mokhtarian;Sadegh Abbasi
曲率尺度空间（CSS）图像的极大值已被用于表示二维形状在不同的应用。该表示在相似性变换下表现出鲁棒性。缩放、方向变化、平移甚至噪声都可以通过表示及其相关的匹配算法轻松处理。在本文中，我们研究了一般仿射变换下的表示的鲁棒性。我们有一个包含1100张海洋生物图片的数据库。该数据库中的等高线显示了很大范围的形状变化。使用500个真实的对象边界和4500个轮廓（它们是真实的对象的仿射变换版本）构建了5000个轮廓的数据库。然后使用CSS表示从原型数据库中查找类似的形状。结果提供了大量的证据的CSS图像的稳定性和仿射变换下的轮廓极大值。该方法还通过一个大型的分类数据库进行了客观的评估，并将其性能与两种著名的方法，即傅立叶描述符和不变矩的性能进行了比较。CSS形状描述符已被选择用于MPEG-7标准化。
The maxima of curvature scale space (CSS) image have already been used to represent 2-D shapes in different applications. The representation has shown robustness under the similarity transformations. Scaling, orientation changes, translation and even noise can be easily handled by the representation and its associated matching algorithm. In this paper, we examine the robustness of the representation under general affine transforms. We have a database of 1100 images of marine creatures. The contours in this database demonstrate a great range of shape variation. A database of 5000 contours has been constructed using 500 real object boundaries and 4500 contours which are the affine transformed versions of real objects. The CSS representation is then used to find similar shapes from this prototype database. The results provide substantial evidence of stability of the CSS image and its contour maxima under affine transformation. The method is also evaluated objectively through a large classified database and its performance is compared with the performance of two well-known methods, namely Fourier descriptors and moment invariants. The CSS shape descriptor has been selected for MPEG-7 standardization.