基于最大似然估计准则的特征匹配点提纯算法

图像特征匹配的准确度直接影响着图像分析与处理的效率与性能，所以要对图像的特征匹配点进行提纯和过滤。首先使用SIFT算法从图像中提取显著特征，建立粗略的匹配关系，利用最近邻比策略初始化特征匹配点的匹配概率，然后基于混合模型的最大似然估计采用EM算法建立匹配点之间的空间转换模型。EM迭代收敛之后，通过其对应关系过滤掉错误的匹配点。实验数据表明，本方法提纯的平均精度可以达到96.8%，平均召回率为81.6%，平均时间消耗为3.1 s。采用该方法提取到的正确匹配点数高于其他算法，同时对包括大视角差、光线变化和仿射变换等大多数变换具有鲁棒性。

Feature matching-point purification algorithm based on maximum likelihood

The matching accuracy of image-pair features directly affected the efficiency and performance of subsequent image analysis and processing, so it was necessary to purify and filter the feature matching-points of the image-pair. Firstly, using the SIFT(scale-invariant feature transform) algorithm to extracted the salient features from the image and established a rough matching relationship. And applying the nearest neighbor ratio to initialized the matching probability. Then, using EM(expectation-maximization) to established a spatial transformation model between matching-points based on the maximum likelihood of the hybrid model. After the EM iteration converged, utilizing the correspondences to filtered out the wrong matching-points. The experimental results demonstrate that the average accuracy of the proposed method can reach 96.8%, the average recall rate is 81.6%, the mean time consumption is 3.1 s. This method is higher than other algorithm on the extracting number of correct matching point-pairs and is robust for most cases including a large viewing angle, image rotation and affine transformation.