一类新的V描述子在形状识别中的应用

A Novel V-System Descriptor in Shape Recognition

提出了一类新的V描述子,对二维图形进行V变换提取形状信息,并定义归一化后的变换系数为描述子,其具有旋转、平移、缩放不变性,通过形状主方向在一定程度上消除了起始点的影响.通过快速V变换可以有效地计算出V描述子,该识别算法采用加权欧氏距离,并充分利用了V描述子的多分辨率分析特性,对轻微遮挡具有一定的抵抗力,可以根据实际情况达到较好的识别.

In this paper, we present a novel V-system descriptor for 2D models; the descriptor is invariant against the rotation, translation, scale transform, and can remove the effect of the arbitrary start point of the shape through the principal orientation. We show that V-system descriptor can be computed efficiently by the fast V-system transformation, and be good at using multi resolution analysis through weighted Euclidean distance. So the new V-system descriptor has some resistance to slightly occlusion, and may achieve good recognition property according to the actual situation.