In order to reduce the proportion of outliers in feature point matching, we propose a feature point matching optimization algorithm based on a wasserstein distance and apply the algorithm to the grid cell model. The wasserstein distance is introduced to calculate the similarity of the distribution of feature points in the grids around each pair of matching points, and the outer points are eliminated by the similarity. We compare the algorithm with the robust algorithm in OpenCV, and the experimental results show that the precision of our algorithm is higher than robust, and the recall is smaller. We open source our implementations at https://github.com/liuzhenboo/Optimization-of-Feature-Point-Matching-Algorithm-Based-on-Wasserstein-Distance.