Classification of maize seeds of different years based on hyperspectral imaging and model updating

Seed classification and identification exhibit potential for detecting seed purity and increasing crop yield. In this study, hyperspectral imaging was employed to develop classification methods for maize seeds. A total of 2000 seeds, including four varieties of maize seeds of different years, were evaluated. Hyperspectral reflectance images were acquired between 400 nm and 1000 nm. Classification models based on the mean spectral features of seeds were developed using least squares support vector machine (LSSVM). Model updating using incremental support vector data description was also applied to update the LSSVM model online and ensure accurate identification of maize seeds of different years. The classification accuracy of the LSSVM model combined with model updating reached 94.4% and was 10.3% higher than that of other non-updated models. This study showed that combined hyperspectral imaging and model updating could be an effective method for classification of seeds of different years. (C) 2016 Elsevier B.V. All rights reserved.