In order to classify tomatoes nondestructively,this paper put forward method，an image technology to predict tomato weight automatically. The algorithm was based on Matlab platform,using mathematical morphological operation and image local property operation to establish identification algorithm for the tomato. Linear model,second order polynomial model,power model were established through analyzing the relations between tomato external parameters and weight. Weight prediction model was established through regression analysis of the external characteristics. The experiment results showed that the weight was highly related to its area,perimeter,maximum inscribed circle diameter and minimum circumscribed circle diameter. Test results showed that the multivariate linear prediction model was the best. Its determination coefficient (R2) was 0.926 7,the standard deviation (SE) was 4.32. Its mean relative error was 1.535%,and the mean absolute error was 3.260 g. The experiment results show that the program can quickly predict tomato weight through tomato external features.