We have recently developed a rapid online line-scan imaging system capable of both hyperspectral Vis/NIR reflectance and fluorescence in the Vis with UV-A excitation. The hyperspectral online line-scan system was integrated with a commercial apple-sorting machine and evaluated to inspect apples for fecal contamination and defects at a processing line speed of over three apples per second. Results showed that fluorescence imaging (using a two-band ratio) could achieve detection of fecal spots on artificially contaminated apples with a 100% detection rate and no false positives regardless of the presence of defects. A NIR two-band reflectance ratio coupled with a simple classification method based on the mean intensity and homogeneity of the ratio achieved a 99.5% apple defect classification accuracy with a false positive rate of only 2%. The presented NIR processing regime overcame the presence of stem/calyx on apples that typically has been a problematic source for false positives in the detection of defects. The most significant and important outcome of this investigation is a line-scan inspection system that can potentially provide the capability for current sorting mechanisms, such as by size and color, as well as additional sorting for quality and safety attributes of food products. This line-scan based online imaging system offers great potential as a value-added dynamic inspection system due to its capability for multi-tasking to meet a variety of inspection objectives. A multi-tasking inspection system that can meet current industry sorting needs with the added benefit of safety inspection without requiring significant modification of existing infrastructure or incurring significant costs may lead the apple industry to consider adopting voluntary measures to further enhance safe production and processing of fruits.

As adulteration of foodstuffs with Sudan dye, especially paprika- and chilli-containing products, has been reported with some frequency, this issue has become one focal point for addressing food safety. FTIR spectroscopy has been used extensively as an analytical method for quality control and safety determination for food products. Thus, the use of FTIR spectroscopy for rapid determination of Sudan dye in paprika powder was investigated in this study. A net analyte signal (NAS)-based methodology, named HLA/GO (hybrid linear analysis in the literature), was applied to FTIR spectral data to predict Sudan dye concentration. The calibration and validation sets were designed to evaluate the performance of the multivariate method. The obtained results had a high determination coefficient (R) of 0.98 and low root mean square error (RMSE) of 0.026% for the calibration set, and an R of 0.97 and RMSE of 0.05% for the validation set. The model was further validated using a second validation set and through the figures of merit, such as sensitivity, selectivity, and limits of detection and quantification. The proposed technique of FTIR combined with HLA/GO is rapid, simple and low cost, making this approach advantageous when compared with the main alternative methods based on liquid chromatography (LC) techniques.

Conventional methods used to evaluate seeds viability are destructive, time consuming, and require the use of chemicals, which are not feasible to implement to process plant in seed industry. In this study, the effectiveness of Fourier transform near infrared (FT-NIR) spectroscopy to differentiate between viable and nonviable watermelon seeds was investigated. Methods: FT-NIR reflectance spectra of both viable and non-viable (aging) seeds were collected in the range of 4,000-10,000 cm-1 (1,000-2,500 nm). To differentiate between viable and non-viable seeds, a multivariate classification model was developed with partial least square discrimination analysis (PLS-DA). Results: The calibration and validation set derived from the PLS-DA model classified viable and non-viable seeds with 100% accuracy. The beta coefficient of PLS-DA, which represented spectral difference between viable and non-viable seeds, showed that change in the chemical component of the seed membrane (such as lipids and proteins) might be responsible for the germination ability of the seeds. Conclusions: The results demonstrate the possibility of using FT-NIR spectroscopy to separate seeds based on viability, which could be used in the development of an online sorting technique.

The objective of this study was to quantify the chemical content of multiple products using one single calibration model. This study involved seven tuber and root powders from arrowroot, Canna edulis , cassava, taro, as well as purple, yellow, and white sweet potato, for partial least square (PLS) regression to predict polysaccharide contents (i.e., amylose, starch, and cellulose). The developed PLS models showed acceptable results, with R c 2 of 0.9, 0.95, and 0.85 and SEC of 2.7%, 3.33%, and 3.22%, for amylose, starch, and cellulose, respectively. The models also successfully predicted polysaccharide contents with R p 2 of 0.89, 0.95, and 0.79; SEP of 2.83%, 3.33%, and 3.55%; and RPD of 3.02, 4.47, and 2.18 for amylose, starch, and cellulose, respectively. These results showed the potential of Fourier transform near-infrared spectroscopy to quantify the chemical composition of multiple products instead of using one individual model.

The inspection of rice grain that may be infected by seedborne disease is important for ensuring uniform plant stands in production fields as well as preventing proliferation of some seedborne diseases. The goal of this study was to use a hyperspectral imaging (HSI) technique to find optimal wavelengths and develop a model for detecting discolored, diseased rice seed infected by bacterial panicle blight (Burkholderia glumae), a seedborne pathogen. For this purpose, the HSI data spanning the visible/near-infrared wavelength region between 400 and 1000 nm were collected for 500 sound and discolored rice seeds. For selecting optimal wavelengths to use for detecting diseased seed, a sequential forward selection (SFS) method combined with various spectral pretreatments was employed. To evaluate performance based on optimal wavelengths, support vector machine (SVM) and linear and quadratic discriminant analysis (LDA and QDA) models were developed for detection of discolored seeds. As a result, the violet and red regions of the visible spectrum were selected as key wavelengths reflecting the characteristics of the discolored rice seeds. When using only two or only three selected wavelengths, all of the classification methods achieved high classification accuracies over 90% for both the calibration and validation sample sets. The results of the study showed that only two to three wavelengths are needed to differentiate between discolored, diseased and sound rice, instead of using the entire HSI wavelength regions. This demonstrates the feasibility of developing a low cost multispectral imaging technology based on these selected wavelengths for non-destructive and high-throughput screening of diseased rice seed.