In recent years, applications of neural network and big data have increased rapidly in agriculture-related areas. At the same time, Deep Neural Network (DNN), in which deep layers are used, achieves much better results especially for classification of big datas properly. In this study, a new DNN model is proposed for the classification of wheat seeds which was taken from UCI Machine Learning Repository. There are totally 210 data from 3 different types of wheat, namely; Kama, Rosa and Canadian. The model is divided into 70% train data and 30% test data. When the developed model was applied to dataset, 100% success rate is achieved in classification of data. In addition, 150,000 pieces of synthetic wheat seed data are generated by using a Fuzzy C-Means based algorithm. The proposed model is tested on different train and test data combinations by using UCI wheat seed and synthetically generated datasets, and 100% success rate was achieved in classification. The proposed model shows that it is the best model compared to other studies in the literature for wheat classifications.