中文摘要：

传统的线性学习图匹配模型具有易于训练和能够求解最优匹配的优点,但是没有考虑图的结构信息,从而限制了其匹配精度.为克服这一缺点,提出一种新的线性学习图匹配模型——基于边特征的学习完全图匹配模型(ELC-GM),其中,边特征由边上采样点的特征描述,而采样点的特征是通过一种包含旋转不变因子的形状上下文特征描述的.ELC-GM先对模型进行有监督的训练,再用Kuhn-Munkres算法求解边匹配,进而用Hungarian解码算法将边匹配转换为点匹配.实验结果表明,ELC-GM的训练效果稳定,匹配精度即使在形变和噪声条件下也能得到一定提升.

英文摘要：

Traditional linear learning graph matching model is easy to be trained and can achieve a global optimal solution. However, this model doesn’t consider the information of graph structure, thus limiting its matching accuracy. To overcome this disadvantage, we propose a novel linear learning graph matchingmodel-edge feature based learning complete graph matching model (ELC-GM). An edge feature is constructedfrom its sampling point features, which are described by an extension of shape context with rotation invariant factors. After supervised training of ELC-GM, Kuhn-Munkres is used to solve the edge match and then Hungarian decoder is applied to determine the final point match. Experimental results show that ELC-GM can achieve good performances with improvement of accuracy, even in cases of deformation and noise.