In order to accurately identify and locate the functional active information

an objective and effective threshold must be found to threshold the statistical parametric map of fMRI. This paper reports a method to threshold the statistical parametric map of fMRI

which combines controlling the false discovery rate with analyzing the spatial correlation of the cortical hemodynamic responses. Firstly

for identifying the active voxels

the proposed method determines threshold based on controlling false discovery rate. Secondly

it analyzes and tests the correlation of hemodynamic responses between the identified active voxels and their 26-neighboring voxels. Not only can it select the threshold adaptively

but can identify the false active voxels caused by stochastic factors

with the strong capability of identifying and locating the functional active information. The proposed method is validated by using both simulation study and real fMRI data analysis.