Software cost estimation is a key open issue for the software industry, which suffers from cost overruns frequently. As the most popular technique for object-oriented software cost estimation, use case points(UCP) method, however, has two major drawbacks: the uncertainty of the cost factors and the abrupt classification. To address these two issues, we propose the extended use case points (EUCP) method. With a probabilistic cost model constructed from integrating fuzzy set theory and Bayesian belief networks(BBNs) with the UCP method, EUCP provides a probability distribution of cost and a refined gradual classification, which mitigate the uncertainty of cost factors and improve the accuracy of classification. In this paper, we provides two case studies to demonstrate the effectiveness of EUCP in the real life.