Abstract

Seed aging detection and viable seed prediction are of great significance in alfalfa seed production, but traditional methods are disposable and destructive. Therefore, the establishment of a rapid and non-destructive seed screening method is necessary in seed industry and research. In this study, we used multispectral imaging technology to collect morphological features and spectral traits of aging alfalfa seeds with different storage years. Then, we employed five multivariate analysis methods, i.e., principal component analysis (PCA), linear discrimination analysis (LDA), support vector machines (SVM), random forest (RF) and normalized canonical discriminant analysis (nCDA) to predict aged and viable seeds. The results revealed that the mean light reflectance was significantly different at 450~690 nm between non-aged and aged seeds. LDA model held high accuracy (99.8~100.0%) in distinguishing aged seeds from non-aged seeds, higher than those of SVM (87.4~99.3%) and RF (84.6~99.3%). Furthermore, dead seeds could be distinguished from the aged seeds, with accuracies of 69.7%, 72.0% and 97.6% in RF, SVM and LDA, respectively. The accuracy of nCDA in predicting the germination of aged seeds ranged from 75.0% to 100.0%. In summary, we described a nondestructive, rapid and high-throughput approach to screen aged seeds with various viabilities in alfalfa.

Highlights

  • Seed aging is an irreversible and natural process in which the vigor of seeds declines or loses completely

  • By combining principal component analysis (PCA), support vector machines (SVM), random forest (RF) and linear discrimination analysis (LDA) together, we found that LDA model had the best performances on the differentiation and prediction of aged and non-aged seeds

  • Spectral features of seeds are related to species, physiologit is difficultMorphological to distinguish and aged seeds and non-aged seeds by visual inspection or tradiical status, substance content, etc., which can be used for seed classification

Read more

Summary

Introduction

Seed aging is an irreversible and natural process in which the vigor of seeds declines or loses completely. The traditional inspection of aged seeds is based on the indicators of color and aroma, germination test, tetrazole staining [4,5,6], etc. All these methods are time-consuming, and the seed cannot maintain its original state, including when being discarded [7,8]. Tigabu and Oden [13] applied NIRS into the detection of viability detection of Masson pine seeds and found that the seeds with different aging times (3 d, 7 d, and 9 d) were identified with an accuracy of 80%. NIRS is an optical spectroscopy method that successfully noninvasively characterizes seeds, it only employs infrared light with 1000–2500 nm wavelength range and cannot cover spectral data similar to other spectral techniques, such as hyperspectral imaging (HSI)

Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call