Based reasoning data fusion method, Dempster-Shafer evidence reasoning applies to class of rounded fruits recognition experiments. Through the use of multiple sensors to observe the fruits of information, sampling, extracting characteristic information to determine the treatment of various sensors measuring the basic belief assignment fruit, and then Dempster combination rule to fuse the data further and improve reliability, the final identification of the effective decision-making a type of fruit. This experiment shows the D-S evidence reasoning has a strong ability to deal with uncertain information, the result proved the correctness and effectiveness. http://www.sjie.org/paperInfo.aspx?ID=1334
