Abstract
Moisture content (MC) is one of the important factors to assess the quality of maize seeds. In this study, the feasibility of using long-wave near infrared (LWNIR) hyperspectral imaging (HSI) technique with the spectral range of 930-2548 nm for predicting MC of single maize seeds was observed. The averaged spectra extracted from whole and centroid regions in the embryo side of single maize seeds were pretreated by Savizky-Golay smoothing and first derivative (SG-D1). A combination of uninformative variable elimination (UVE) and successive projections algorithm (SPA) was proposed to select feature wavelengths (variables) from LWNIR hyperspectral data. The quantitative relationship between feature wavelengths and MC was established by partial least square (PLSR) and least square-support vector machine (LS-SVM), respectively. Results illustrated that the UVE-SPA-LS-SVM model established based on spectra of centroid region obtained the best performance for MC detection of the single maize seeds. The correlation coefficient of prediction (Rpre) and root mean square error of prediction (RMSEP) were 0.9325 and 1.2109, respectively. Finally, MC distribution of single maize seed was visualized by pseudo-color map. This study showed LWNIR HSI technique was feasible to measure MC of single maize seeds and a robust and accurate model could be established based on UVE-SPA-LS-SVM method with the spectra of centroid regions.
Highlights
Maize is an important source of energy and one of the main cereals in the world [1]
The main objectives of this article were: (1) to collect the long-wave near infrared (LWNIR) hyperspectral images of maize seedsand separately extract the average spectra from whole seed region and centroid region; (2) to select feature variables that were the most informative for determination of Moisture content (MC) of seeds by variable selection algorithms of uninformative variable elimination (UVE) and successive projections algorithm (SPA); (3) to build the partial least squares regression (PLSR)linear models and least square-support vector machine (LS-support vector machines (SVM)) nonlinear models based on feature variables for MC detection; and (4) to visualize the spatial distribution of MC of single maize seeds
In this study, the long-wave NIR hyperspectral imaging (9302548 nm) coupled with UVE-SPA combination variable selection algorithm and LS-SVM model was successfully utilized for determining the MC of maize seeds
Summary
Maize is an important source of energy and one of the main cereals in the world [1]. Moisture content (MC) is one of the critical factors to assess seeds quality. It directly affects the storage [2, 3]. The methods used to detect the MC of agricultural products can be divided into two types of direct methods and indirect methods. The former mainly contains drying and Karl Fischer methods [9]. The latter includes capacitance, conductance, and microwave methods [10]. These methods could achieve the rapid and nondestructive MC determination. It is very meaningful to find a rapid, low VOLUME XX, 2020
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
