The research on the application of electronic nose in discriminate the rice varieties

摘要

In order to identify rapidly and avoid hybrids of different rice varieties, electronic nose (E-nose) is used to test rice of different varieties and valid information is obtained. Five types of features are extracted from the obtained information. The different rice varieties are distinguished by principal component analysis (PCA), Fisher discriminant analysis (FDA) and RBF neural network, the results of the three identification methods are compared and analyzed. The results show that: different rice varieties can be distinguished with the proper methods of feature extraction and pattern recognition; it is an effective way to distinguish different rice varieties by the E-nose.