Motived by that clustering by fast search and find of density peaks algorithm(CFSFDP) could not select the cluster center automatically, an improved CFSFDP algorithm was presented. The improved method uses the weighted average method and calculates the weighted averages of center weight for each point as the screening indices of cluster center. The data point will be selected as cluster center if its center weight is greater than the calculated weighted average. With aforesaid method, the improved algorithm could select the cluster center automatically, and effectively avoid the err by human made according to the decision graph. Simulation experiments comparing with K-means and CFSFDP on 4 kinds of UCI datasets are shown that the improved algorithm could retain the accurate and fast characteristics of CFSFDP and select the cluster center automatically.