Screening of maize haploid kernels based on near infrared spectroscopy quantitative analysis

Cui, Yongjin; Ge, Wenzhang; Li, Jia; Zhang, Junwen; An, Dong; Wei, Yaoguang

doi:10.1016/j.compag.2019.01.038

Cited by 25 publications

(16 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Accurate identification of 17 varieties of maize seeds was feasible using vector fusion of spectral features and image features (morphology and texture) [18]. Cui et al explored a method for corn haploid seed screening and verified it with partial least squares regression (PLSR) [19].…”

Section: Related Workmentioning

confidence: 99%

Rapid Vitality Estimation and Prediction of Corn Seeds Based on Spectra and Images Using Deep Learning and Hyperspectral Imaging Techniques

et al. 2020

View full text Add to dashboard Cite

Highly viable seeds are of great significance for agricultural development, and the traditional corn seed vigor detection method is time-consuming and laborious. In this paper, the spectral and image information of hyperspectral imaging was used, and a distinction between seed vigor detection and prediction was proposed. The potential of hyperspectral imaging technology and convolutional neural networks (CNNs) to identify and predict maize seed vitality was evaluated. The hyperspectral information in 10 hours before the germination of four vigor level seeds (144 samples each) was collected. A support vector machine, extreme learning machine, and one-dimensional convolutional neural network (1DCNN) were used to model the spectral data set, comparing the effects of multidimensional scattering correction and principal component analysis. 1DCNN performed best on the original spectral data, reaching an accurate recognition of 90.11%. According to the spectral changes of the seed germination, the first three hours of data were selected for prediction, which had higher recognition accuracy than the test set. The image-based 2DCNN model achieved 99.96% accurate recognition at a fast convergence speed. By differentiating the spectra and image information, the various CNN models can achieve accurate detection and prediction, providing a framework to advance research on seed germination.

show abstract

Section: Related Workmentioning

confidence: 99%

Rapid Vitality Estimation and Prediction of Corn Seeds Based on Spectra and Images Using Deep Learning and Hyperspectral Imaging Techniques

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This slight enhancement can be explained by the anthocyanin expressiveness, where there may be spots on the embryo‐down side that would facilitate the distinction between haploid and inhibited seeds. Some studies have used hyperspectral images (Wang et al., 2018) or NIR (Cui et al., 2019) of both sides of seeds from induction crosses to classify them into haploid and diploid seeds. These studies showed that the distinction between embryo‐up and embryo‐down images was more accurate than the haploid and diploid classes.…”

Section: Discussionmentioning

confidence: 99%

Improving the identification of haploid maize seeds using convolutional neural networks

et al. 2021

View full text Add to dashboard Cite

A critical step toward the success of the doubled haploid (DH) technique is the haploid identification within induction crosses. The R1-nj marker is the principal mechanism employed in this task enabling the selection of haploids at the seed stage. Although it seems easy to identify haploid seeds, this task is performed manually by visual classification, which becomes an inefficient process in terms of time and labor. Also, differential phenotypic expression of the R1-nj marker results in high rates of false positives among haploid seeds. For the first time, an image-based convolutional neural network (CNN) was trained to identify true positives among putative haploid seeds. The experiment was conducted using 3,000 maize (Zea mays L.) seeds from induction crosses classified as haploid (1,000), diploid (1,000), and inhibited (1,000) class. Images were taken from each seed, and then seeds were planted in the field to confirm their ploidy. For putative haploids (R1-nj phenotype), the classification accuracy on average was 94.39%, 97.07% for the haploid class, and 91.71% for the diploid class. However, the CNN model was unable to distinguish true haploid seeds among the putative haploid class, which indicates that CNN did not recognize different patterns between them. Finally, we provided a highly accurate and trained CNN model to the scientific community to classify haploid maize seeds via R1-nj, which can support maize breeders to optimize DH pipelines, mainly for small breeding programs with limited resources.

show abstract

“…Machine learning algorithms or deep belief networks were used to construct a haploid selection model to analyze the NIR spectral data, and the haploid sorting accuracy reached over 90% [ 32 , 33 ]. A quantitative analysis method based on the spectral features of the oil content of kernels was developed to sort haploids, and the haploid sorting accuracy was above 90% [ 34 , 35 ]. The spectral method provides a new concept in haploid sorting; however, repeated modeling will take a long time, and no equipment has yet been developed based on the spectra for the automatic sorting of maize haploid kernels.…”

Section: Introductionmentioning

confidence: 99%

Improving the sorting efficiency of maize haploid kernels using an NMR-based method with oil content double thresholds

Liu

Zhang

et al. 2021

Plant Methods

View full text Add to dashboard Cite

Background Maize haploid breeding technology can be used to rapidly develop homozygous lines, significantly shorten the breeding cycle and improve breeding efficiency. Rapid and accurate sorting haploid kernels is a prerequisite for the large-scale application of this technology. At present, the automatic haploid sorting based on nuclear magnetic resonance (NMR) using a single threshold method has been realized. However, embryo-aborted (EmA) kernels are usually produced during in vivo haploid induction, and both haploids and EmA kernels have lower oil content and are separated together using a single threshold method based on NMR. This leads to a higher haploid false discrimination rate (FDR) and requires secondary manual sorting to select the haploid kernels from the mixtures, which increases the sorting cost and decreases the haploid sorting efficiency. In order to improve the correct discrimination rate (CDR) in sorting haploids, a method to distinguish EmA kernels is required. Results Single kernel weight and oil content were measured for the diploid, haploid, and EmA kernels derived from three maize hybrids and nine inbred lines by in vivo induction. The results showed that the distribution of oil content showed defined boundaries between the three types of kernels, while the single kernel weight didn't. According to the distribution of oil content in the three types of kernels, a double-threshold method was proposed to distinguish the embryo-aborted kernels, haploid and diploid kernels based on NMR and their oil content. The double thresholds were set based on the minimum oil content of diploid kernels and the maximum content of EmA kernels as the upper and lower boundary values, respectively. The CDR of EmA kernels in different maize materials was > 97.8%, and the average FDR was reduced by 27.9 percent. Conclusions The oil content is an appropriate indicator to discriminate diploid, haploid and EmA kernels. An oil content double-threshold method based on NMR was first developed in this study to identify the three types of kernels. This methodology could reduce the FDR of haploids and improve the sorting efficiency of automated sorting system. Thus, this technique represents a potentially efficient method for haploid sorting and provides a reference for the process of automated sorting of haploid kernels with high efficiency using NMR.

show abstract

Screening of maize haploid kernels based on near infrared spectroscopy quantitative analysis

Cited by 25 publications

References 19 publications

Rapid Vitality Estimation and Prediction of Corn Seeds Based on Spectra and Images Using Deep Learning and Hyperspectral Imaging Techniques

Rapid Vitality Estimation and Prediction of Corn Seeds Based on Spectra and Images Using Deep Learning and Hyperspectral Imaging Techniques

Improving the identification of haploid maize seeds using convolutional neural networks

Improving the sorting efficiency of maize haploid kernels using an NMR-based method with oil content double thresholds

Contact Info

Product

Resources

About