The long time consumption is a bottleneck for the applicability of the ghost imaging (GI). By introducing a criterion for the convergence of GI, a factor was investigated that impacts on the convergence speed of it. Based on computer experiments, it’s demonstrated that the object’s feature size relative to the spatial coherent length of the illuminating light impacts on the necessary number of uncorrelated data being acquired for the correlation computation. It may motivate people to seek ways towards real-time practical applications of GI and its analogues. In addition, the method to simulate the uncorrelated sequence of a complex ensemble for thermal light is valuable in applications where actively controlling the light fields is needed.