When the images compressed by traditional transformation compression a lgorithms are transmitted over wireless channels,if Gaussian random interference causes the loss of the c rucial transformation coefficients, the contents of the reconstructed images will be lost obviously and this will re duce the accuracy of the subsequent detection and recognition results greatly.In order to solve this problem,based on the characteristics of equal importance about each compressed sensing component,this paper first analyzes th e feasibility of resisting the interference by removing the distorted compressed sensing signal components,the n proposes an anti-interference image reconstruction algorithm.This algorithm f irst confirms the new compressed sensing signals and the new reconstruction matrix based on the locations of the corresponding compressed sen sing signal components of the Gaussian-interfered bits,and then reconstructs the original images employing t he iterative threshold algorithm. The simulation results demonstrate that our algorithm can reconstruct exact im ages at low bit error rates,and inexact images whose qualities are slightly lowered without loss of local conte nts at high bit error rates.As a result,our algorithm can overcome the deficiency in anti-interference abilit y of transformation compression algorithms and the iterative threshold algorithm,thus proposes a feasible scheme for the anti-interference problem that arises in wireless image transmission.