Identifying the “Dangshan” Physiological Disease of Pear Woolliness Response via Feature-Level Fusion of Near-Infrared Spectroscopy and Visual RGB Image

Abstract

The “Dangshan” pear woolliness response is a physiological disease that causes large losses for fruit farmers and nutrient inadequacies.The cause of this disease is predominantly a shortage of boron and calcium in the pear and water loss from the pear. This paper used the fusion of near-infrared Spectroscopy (NIRS) and Computer Vision Technology (CVS) to detect the woolliness response disease of “Dangshan” pears. This paper employs the merging of NIRS features and image features for the detection of “Dangshan” pear woolliness response disease. Near-infrared Spectroscopy (NIRS) reflects information on organic matter containing hydrogen groups and other components in various biochemical structures in the sample under test, and Computer Vision Technology (CVS) captures image information on the disease. This study compares the results of different fusion models. Compared with other strategies, the fusion model combining spectral features and image features had better performance. These fusion models have better model effects than single-feature models, and the effects of these models may vary according to different image depth features selected for fusion modeling. Therefore, the model results of fusion modeling using different image depth features are further compared. The results show that the deeper the depth model in this study, the better the fusion modeling effect of the extracted image features and spectral features. The combination of the MLP classification model and the Xception convolutional neural classification network fused with the NIR spectral features and image features extracted, respectively, was the best combination, with accuracy (0.972), precision (0.974), recall (0.972), and F1 (0.972) of this model being the highest compared to the other models. This article illustrates that the accuracy of the “Dangshan” pear woolliness response disease may be considerably enhanced using the fusion of near-infrared spectra and image-based neural network features. It also provides a theoretical basis for the nondestructive detection of several techniques of spectra and pictures.

The Nondestructive Model of Near-Infrared Spectroscopy with Different Pretreatment Transformation for Predicting “Dangshan” Pear Woolliness Disease

“…Team member Yuanfeng Chen achieved excellent results in predicting DPWD by integrating the near-infrared spectroscopy data and features of corresponding sample images of "Dangshan" pear [20], based on the near-infrared spectroscopy data and images of "Dangshan" pear. However, in the process of collecting pear fruit sample photos, stable light sources and professional shooting equipment are needed, which are difficult to obtain in actual agricultural production.…”

Successful Applications of NIR Spectroscopy and NIR Imaging in the Food Processing Chain

“…The present Special Issue was developed within this framework with the aim of collecting scientific articles showing the potential of NIRS, coupled or not with imaging techniques, for new, diverse, and innovative real industrial applications. The impressive flexibility of NIRS is shown in the collected articles, which span from the in-line estimation of fat marbling in whole beef striploin by NIR hyperspectral imaging [ 1 ] to the in-line application of NIRS for quality monitoring in a large-scale cheese production plant [ 2 ]; from the discrimination of normal vs. dark, firm, and dry (DFD) beef meat and the prediction of quality traits [ 3 ] to the amino acid profiling of quality protein maize [ 4 ]; from the tracking of sugar content distribution of white strawberry by NIR hyperspectral imaging [ 5 ] to the estimation of black root mould infection in apples [ 6 ], and the detection of the “Dangshan” physiological disease of pears [ 7 ].…”