For many years, one of the problems in pattern recognition is classification. There are many methods proposed to deal with this type of problem. The data sets are sometimes in the binary form (real number) and represented by vectors of binary numbers (real numbers) although there are uncertainties in the data. This study is concerned with a linguistic perceptron with vectors of fuzzy numbers as inputs. This algorithm is based on the extension principle and the decomposition theorem. A synthetic data set has been utilized to illustrate the behavior of this linguistic version of perceptron. We compare the result from the linguistic perceptron with that from the regular perceptron.