Estimation of protein content in wheat samples using NIR hyperspectral imaging and 1D-CNN

Abstract

Wheat protein content is a major determinant of its usage and value. Current methods require wet labs that may be difficult to access and are not real-time. To overcome this, Hyperspectral imaging (HSI) has been reported for estimating the protein content of wheat seeds with the advantage that it is real-time, does not require wet labs, and has high accuracy. However, these models have been developed and validated for a small range of protein content, and without considering cultivation regions. This paper reports the extension of the use of HSI for protein estimation for a wider range of protein content and for wheat cultivated in different regions. Hyperspectral images of 621 wheat samples from five regions in India were acquired in the 900-1700 nm wavelength range. The reference protein content of each sample was determined using the Kjeldahl method, with values ranging from 9.5 to 17.25%. Mean spectra were extracted from the hyperspectral images to develop deep learning and conventional machine learning methods, which were validated through 5-fold cross-validation. The experiments showed that the one-dimensional convolutional neural networks (1D-CNN) performed the best, with the coefficient of determination (R²) of 0.9972, root mean square error (RMSE) of 0.0771, and the ratio of performance to deviation (RPD) of 18.81 for the prediction set. This shows that a 1D-CNN model trained using mean spectra can accurately estimate the wheat protein content. This has the advantage of not requiring a wet lab, and being potentially real-time, which could benefit the farmers, traders, and food industry.

Keywords: Convolutional neural network; Near-infrared hyperspectral imaging; Non-destructive quality evaluation; Spectral data extraction; Wheat protein.

Fig. 1

Map showing the locations across India from which wheat samples were collected.

Fig. 2

The steps involved in hyperspectral image processing and extraction of multiple mean spectra.

Fig. 3

Architecture of the proposed 1D-CNN model for wheat protein estimation.

Fig. 4

The spectral characteristics of wheat samples used in this study.

Fig. 5

Performance evaluation of the 1D-CNN model with different hyperparameters.

Fig. 6

Training and validation loss curves of the 1D-CNN model over 300 epochs.

Fig. 7

Spectral signatures after applying various preprocessing techniques: (a) SNV, (b) MSC, (c) SGS, (d) SG1, (e) SG2, and (f) detrending.

Fig. 8

Impact of spectral preprocessing techniques on 1D-CNN model performance.

Fig. 9

Scatter plot showing the correlation between predicted and actual wheat protein content.

Fig. 10

Impact of the mean spectra count on the RMSE performance of the 1D-CNN model.