Modeling of flaxseed protein, oil content, linoleic acid, and lignan content prediction based on hyperspectral imaging

Abstract

Protein, oil content, linoleic acid, and lignan are several key indicators for evaluating the quality of flaxseed. In order to optimize the testing methods for flaxseed's nutritional quality and enhance the efficiency of screening high-quality flax germplasm resources, we selected 30 flaxseed species widely cultivated in Northwest China as the subjects of our study. Firstly, we gathered hyperspectral information regarding the seeds, along with data on protein, oil content, linoleic acid, and lignan, and utilized the SPXY algorithm to classify the sample set. Subsequently, the spectral data underwent seven distinct preprocessing methods, revealing that the PLSR model exhibited superior performance after being processed with the SG smoothing method. Feature wavelength extraction was carried out using the Successive Projections Algorithm (SPA) and the Competitive Adaptive Reweighted Sampling (CARS). Finally, four quantitative analysis models, namely Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), Multiple Linear Regression (MLR), and Principal Component Regression (PCR), were individually established. Experimental results demonstrated that among all the models for predicting protein content, the SG-CARS-MLR model predicted the best, with and of 0.9563 and 0.9336, with the corresponding Root Mean Square Error Correction (RMSEC) and Root Mean Square Error Prediction (RMSEP) of 0.4892 and 0.5616, respectively. In the optimal prediction models for oil content, linoleic acid and lignan, the ${\text{R}}_{\text{p}}^2$ was 0.8565, 0.8028, 0.9343, and the RMSEP was 0.8682, 0.5404, 0.5384, respectively. The study results show that hyperspectral imaging technology has excellent potential for application in the detection of quality characteristics of flaxseed and provides a new option for the future non-destructive testing of the nutritional quality of flaxseed.

Keywords: flaxseed; hyperspectral imaging; lignan; linoleic acid; oil content; protein.

Figure 1

The hyperspectral imaging system.

Figure 2

Sample hyperspectral image classification mask and spectral extraction flowchart. (A) Hyperspectral image; (B) Classification image; (C) Mask image; (D) Application mask image; (E) Region of interest image; (F) Average spectral curve.

Figure 3

Experimental procedure. (A) Process of raw hyperspectral image acquisition and ROI extraction. (B) Spectral preprocessing, feature extraction, and modeling processes.

Figure 4

Flaxseed spectral reflectance curves. (A) Raw spectral curve of flaxseed; (B) SG preprocess spectral curve of flaxseed; (C) Normalize preprocess spectral curve of flaxseed; (D) Baseline preprocess spectral curve of flaxseed; (E) SNV preprocess spectral curve of flaxseed; (F) MA preprocess spectral curve of flaxseed; (G) MSC preprocess spectral curve; (H) 1stDer preprocess spectral curve.

Figure 5

Protein content prediction results of the PLSR model based on different preprocesses. (A) Raw-PLSR; (B) SG-PLSR; (C) Normalize-PLSR; (D) Baseline-PLSR; (E) SNV-PLSR; (F) MA-PLSR; (G) MSC-PLSR; (H) 1stDer-PLSR.

Figure 6

SPA extraction of feature variables. (A) Trend of RMSE with feature variables, (B) Distribution of preferred feature variables.

Figure 7

The process of extracting feature variables by CARS.

Figure 8

The optimal prediction of proteins based on (A) MLR, (B) PLSR, and (C) PCR models.

Figure 9

Significance map of MLR model for CARS extracted feature bands.

Figure 10

Predicted results of oil content, linoleic acid, and lignan content based on the optimal model SG-SPA-MLR. (A) Oil content prediction results. (B) Results of linoleic acid content prediction. (C) Prediction results of lignan content.

Figure 11

Significance map of MLR model for CARS extracted feature bands. (A) Significance map of the characteristic band of oil content; (B) Significance map of the characteristic band of linoleic acid; (C) Significance map of the characteristic band of lignan.