A robust multiview fuzzy clustering method combining local spatial information

In view of the fact that the existing multi-view clustering algorithm does not dig deep into the local spatial information structure, resulting in inaccurate clustering results, this paper intends to make full use of the correlation and diversity between data to improve the clustering accuracy, and use the local similarity measure to mine the potential in the data. The structure is clustered and analyzed, and the atomic information is merged in a fuzzy manner to maintain the robustness of the algorithm. It is not sensitive to noise and will retain more view structure information. The algorithm (MvNIFC) in this paper verifies the effectiveness of the algorithm through experiments on various data sets, and compares several existing multi-view blur algorithms experimentally. The results show that the clustering accuracy and noise data processing are both improved.