A Reliable Methodology for Determining Seed Viability by Using Hyperspectral Data from Two Sides of Wheat Seeds

Abstract

This study investigated the possibility of using visible and near-infrared (VIS/NIR) hyperspectral imaging techniques to discriminate viable and non-viable wheat seeds. Both sides of individual seeds were subjected to hyperspectral imaging (400–1000 nm) to acquire reflectance spectral data. Four spectral datasets, including the ventral groove side, reverse side, mean (the mean of two sides’ spectra of every seed), and mixture datasets (two sides’ spectra of every seed), were used to construct the models. Classification models, partial least squares discriminant analysis (PLS-DA), and support vector machines (SVM), coupled with some pre-processing methods and successive projections algorithm (SPA), were built for the identification of viable and non-viable seeds. Our results showed that the standard normal variate (SNV)-SPA-PLS-DA model had high classification accuracy for whole seeds (>85.2%) and for viable seeds (>89.5%), and that the prediction set was based on a mixed spectral dataset by only using 16 wavebands. After screening with this model, the final germination of the seed lot could be higher than 89.5%. Here, we develop a reliable methodology for predicting the viability of wheat seeds, showing that the VIS/NIR hyperspectral imaging is an accurate technique for the classification of viable and non-viable wheat seeds in a non-destructive manner.

Detection of viability of soybean seed based on fluorescence hyperspectra and CARS‐SVM‐AdaBoost model

“…The results showed that the AdaBoost algorithm could greatly improve the classification performance of the original model. Compared with the current related study using NIR or HSI technology (Al‐Amery et al, ; Zhang et al, ), FHSI technology combined with the optimization model reduced the data dimension of the model and improved the discrimination accuracy of viable and nonviable seeds. In summary, the developed model CARS‐SVM‐AdaBoost not only had a satisfactory classification effect, but also had good stability of the model.…”

“…Moreover, FT‐NIR technology combined with PLS‐DA model was applied for the viability detection of crop seeds such as corn (Ambrose, Lohumi, Lee, & Cho, ) and soybean (Kusumaningrum et al, ), and the satisfactory results were achieved. In addition, HSI technology coupled with suitable model was successfully applied in the identification of viable and nonviable muskmelon seeds (Kandpal, Lohumi, Kim, Kang, & Cho, ), wheat (Zhang et al, ), and other seeds.…”

Evaluating green tea quality based on multisensor data fusion combining hyperspectral imaging and olfactory visualization systems

“…A variety of kernel functions exist, namely, linear kernel function, radial basis function (RBF), polynomial kernel function, and polynomial function. In the present study, SVM was built using RBF because previous researches confirm that RBF is a more compatible supported kernel function . The penalty coefficient ( c ) of the SVM model and the kernel width ( g ) of the kernel function must be determined.…”

“…In the present study, SVM was built using RBF because previous researches confirm that RBF is a more compatible supported kernel function. [26][27][28] The penalty coefficient (c) of the SVM model and the kernel width (g) of the kernel function must be determined. The optimal combination of (c, g) was determined by a grid-search procedure and the ranges of c and g were both 2 −10 to 2 10 .…”

Spectral-Spatial Feature Extraction of Hyperspectral Images Based on Propagation Filter

“…Hyperspectral images (HSIs) have many spectral bands and complex spatial structures that contain abundant information [ 1 , 2 ]. Therefore, HSIs are widely applied in areas such as ocean monitoring [ 3 , 4 ], precision agriculture [ 5 , 6 ], forest degradation statistics [ 7 ] and military reconnaissance [ 8 ]. However, the high-dimensional spectral features of HSIs may cause the Hughes phenomenon [ 9 , 10 ], leading to a decrease in HSI classification accuracy [ 11 , 12 , 13 ].…”