With the rapid development of optical measurement techniques, monitoring heavy metal content in soil with hyperspectral image is a very important. Spectroscopic techniques are capable of higher speed, lower cost and less damage, which providing a better method for monitoring heavy metals in soil for environmental protecting purposes. This paper proposes a new insight of multiple regression in applying the hyperspectral image data to the estimation of heavy metals concentration, e.g. mercury content in soil. The sample points were scanned by a spectroradiometer within a wavelength region from 325 to 1075 nm. The data of hyperspectral images measured from the soil is preprocessed in the experiment, and the methods include resampling, first-order differential, and continuum removal, etc.. The algorithms of stepwise multiple regression are established accordingly, and the accuracy of each equation is tested. The analysis results showed that the accuracy of reciprocal logarithm works better than other methods, which has shown that it is feasible to predict the content of mercury by using stepwise multiple regression.