Electrical capacitance tomography (ECT) is a promising technology for visualization of permittivity distributions inside a volume. Fast and high spatial resolution algorithm is still a challenging task. In this paper, we present a novel soft-thresholding iterative method for ECT image reconstruction. An adaptive selection of regulation parameter is proposed based on the capacitance error in the Landweber algorithm. Both simulation and experimental results show that the image quality of the new method is comparable to that of the projected Landweber method, and in most test cases, the new method is faster than the projected Landweber method.