Considering the big uncertainty and incomplete information of radar network measurement data, the concept of analogy decision tree is created and a feature-level fusion recognition algorithm based on decision tree analogy is proposed. The proposed algorithm uses a way of while constructing while classifying without training samples. The greatest information gain property feature is selected as the classification feature to classify the measurement data, which achieves the goal of recognizing the target. The algorithm can deal with the measurement data containing vacancies and makes full use of measurement data. Simulation results show that the analogy decision tree classification algorithm is a simple and effective feature-level fusion recognition algorithm.