Non-destructive detection and classification of in-shell insect-infested almonds based on multispectral imaging technology

Abstract

The feasibility of non-destructive detection and classification of in-shell insect-infested almonds was examined by using multispectral imaging (MSI) technology combined with chemometrics. Differentiation of reflectance spectral data between intact and insect-infested almonds was attempted by using analytical approaches based on principal component analysis and support vector machines, classification accuracy rates as high as 99.1% in the calibration set and 97.5% in the prediction set were achieved. Meanwhile, the in-shell almonds were categorized into three classes (intact, slightly infested and severely infested) based on the degree of damage caused by insect infestation and were characterized quantitatively by the analysis of shell/kernel weight ratio. A three-class model for the identification of intact, slightly infested and severely infested almonds yielded acceptable classification performance (95.6% accuracy in the calibration set and 93.3% in the prediction set). These results revealed that MSI technology combined with chemometrics may be a promising approach for the non-destructive detection of hidden insect damage in almonds and could be used for industrial applications.

Postharvest processing of tree nuts: Current status and future prospects—A comprehensive review

“…Such processes are shown in Figure 4. Currently, there are three major problems with this procedure: (1) The large amount of dust generated during the sweeping and picking up spreads away in the air, causing pollution and impacts human health (Baticados et al., 2019); (2) The almonds directly contact the soil for long periods of time during natural drying, which introduces a pathway for severe insect damage and contamination by pathogenic microbials (Gradziel et al., 2000, 2020; Wang et al., 2013; Yu et al., 2018); (3) There is no technology available for monitoring and detecting insects during stockpiling and storage, which results in a significant product loss due to insect damage or a large amount of chemicals use from frequent fumigation. In Europe, almonds mainly grow in Spain, and are harvested off‐ground and de‐hulled in‐field.…”

Processing of Tree Nuts

“…The stockpiles are aerated, which allows the product moisture to equilibrate before mechanically cleaned and de-hulled with abrasive huller [33]. Currently, two major problems with this procedure are: (1) the sweeping and picking up generate large amount of dust, which spreads away in the air and causes pollution [34]; (2) almonds contact the soil directly while drying on-ground, which induces severe insect damage and microbial spoilage [35,36]. In Europe (mainly Spain), almonds are harvested off-ground and de-hulled in-field, which are then dried in silo dryers with air [31].…”

“…The insects could hide in dried nuts for a long time. In recent years, damaged nuts and live insects have been found in dried nuts or nut-containing products [35]. Insect infestation is also favorable for mold growth [75].…”

Porcelain Insulator Crack Location and Surface States Pattern Recognition Based on Hyperspectral Technology

“…For example, the hyperspectral method was used to detect cracks in paintings to quantify cultural heritage [ 9 , 10 ]. Zhang et al applied this approach to crop defect detection, as well as other quality and safety detection methods [ 11 , 12 , 13 , 14 ]. Wang et al applied the hyperspectral method in the field of geographical remote sensing terrain classification [ 15 , 16 , 17 , 18 , 19 ].…”