微分几何编码识别物体的形状

为更好地识别目标形状，编码方法需要对目标的刚体变换具有不变性，同时最大限度保持目标的原有信息。鉴于刚体平面曲线作变换时其曲率的不变性，提出了基于轮廓曲率提取的目标边界编码方法，并对此方法实施了离散化处理。提出了基于改进的KMP算法（D.K.Knuth，V.R.Pratt和J．H．Morris）的曲线匹配方法，并对目标轮廓的重建作了描述。实验证明，利用微分几何的思想描述目标边界，提取方法简单，存储量小，其编码针对目标刚体变换具有不变性，为识别提供了较大的方便。

Objects Shape Recognition Using Differential Geometry Code

Coding approaches to object must be invariant under rigid transform and maximally keep the original information in order to get a better recognition result. Considering the invariance of curvature, a new coding approach based on the abstraction of contour curvature is presented and discrete approximation solution has been demonstrated. A new curve-matching algorithm based on improving KMP (D. E. Knuth, V. R. Pratt and J. H. Morris and the reconstruction method to contour is proposed. Experiments indicate a simpler matching algorithm, reduced storage and greater convenience for pattern recognition when the differential geometry approaches is utilized to describe the contour.