The potential of electronic nose to distinguish of wheat seeds was studied. The reproducibility and practicability of electronic nose data was evaluated by repeating the analysis of samples with a time difference of two months. The principle components analysis and linear discriminant analysis were applied to the generated patterns to distinguish the varieties of wheat seeds. The results showed that they could distinguish the wheat varieties properly. The stepwise discriminant analysis and a three-layer backpropagation neural network were developed for pattern prediction models. The results showed that both models could identify the wheat varieties, the back-propagation neural network presented the higher percent of correct classifications in comparison to stepwise discriminant analysis.Moreover, gas chromatographymass spectrometry analysis of the headspaces of same samples confirmed thatelectronic nose as a powerful tool is able to identify thewheat seeds.