Fourier descriptors(FDs) which didn’t change with changes of translation, rotation and scale, and were also independent of the location of the beginning point of the image edge were analyzed. The FDs and Euclidean distance were applied to the recognition of the rice hopper shape. Average discrete degree of sogatella furcifera and rice hopper was calculated to test stability of FDs and coefficients reference value of shape feature was determined. Through 191 sample images tested, it was found that when similarity difference was less 0.0123,error rate of rice hopper was 7.85%. The experiment results indicated that this approach had a good recognition performance.