This chapter reviews progress in developing automated image-based systems for identifying crop insect pests. It identifies the challenges in distinguishing insect pests in field conditions and ways they can be addressed. The chapter outlines key steps in image-based identification (image capture, processing, segmentation, feature extraction and classification) and the growing use of artificial intelligence to increase accuracy and reliability. It also provides examples of commercially-available systems and assesses future developments. The chapter is aimed at practitioners and scientists new to the topic and as a useful reference on the pros and cons of different monitoring strategies for those already in the field.

Pawpaw (Asimina triloba (L.) Dunal, Annonaceae) is a fruit tree native to eastern North America, increasingly grown for commercial production in the United States (Callaway, 1992; Layne, 1996), Europe, and Western Asia (Brannan and Coyle, 2021; Lolletti et al., 2021). In 2012, virus-like symptoms were noticed in a 0.3 ha pawpaw orchard at Michigan State University Plant Pathology Research Station; ~30% of the trees presented symptoms which included foliar mosaic, vein yellowing, and necrosis, and were first mistaken for nutrient (magnesium/zinc) deficiency. Trees were treated for magnesium/zinc deficiency but continued to decline in fruit yield and overall vigor, and typically died within 3─4years after symptoms were first observed (Fig. S1). Preliminary testing using Agdia ImmunoStrips for cucumber mosaic virus, impatiens necrotic spot virus, tobacco mosaic virus, tomato spotted wilt virus and the genus Potyvirus were negative. However, icosahedral virus particles were observed by TEM (Fig. S2). To establish virus identity, we deep-sequenced tissue from a symptomatic pawpaw obtained from same site in summer 2021. Virus particles were purified , and virion-associated nucleic acids (VANA) were extracted using the Purelink viral RNA/DNA kit (Invitrogen) (Maclot et al., 2021). Both viral RNA and DNA were subjected to high-throughput sequencing (HTS) on the Illumina NextSeq 500 platform (GIGA, University of Liege, Belgium). A total of 574,274 trimmed reads (150 nt read length) were de novo assembled using Geneious Prime 2022.2.2 software (https://www.geneious.com) and subjected to BLASTn analysis. Two contigs of 7511 bp (average coverage: 1048) and 3924 bp (average coverage: 3012) showed 94% and 95% nt identities with tobacco ringspot virus (TRSV) RNA1 isolate YW (MT042825) and RNA2 isolate OH19 (MT561435) respectively. These two contigs (Accession no. OP589177 and OP589178) covered the complete TRSV genome for each segment. HTS found no other plant-associated viral / virus-like sequences in this symptomatic pawpaw sample. To further confirm TRSV infection, leaf extract from this sample was tested with RT-PCR using primers specific to the RdRp gene of TRSV RNA1 (Forward, 5'-TAACCTCATTGCAGTTGATCCTT-3'; Reverse, 5'-TAATTCAAGCTCAGGTCTCTTCT-3'; 739 bp amplicon) and the coat protein of TRSV RNA2 (Forward, 5'-TCATGCTTAAAGATGCAGATGTG-3'; Reverse, 5'-TATAAAGCTCCGCACTAGAAAACA-3'; 753 bp amplicon). Sanger sequence analysis showed 99.5% and 99.8% nt identity between the amplicons and the HTS contigs (RNA1 and RNA2 respectively) assembled from the pawpaw sample, and the amplicons likewise matched GenBank TRSV sequences (91.7% and 95.6% nt identities respectively with TRSV RNA1 isolate CmTX-H (MN504766) and TRSV RNA2 isolate IA-1-2017 (MT563079)). We further screened for TRSV infection in leaves from four symptomatic and three non-symptomatic pawpaw trees collected from the same site in 2022. RT-PCR revealed positive infection in all four symptomatic samples and one of the three (33%) non-symptomatic samples. Our results confirm the presence of TRSV infection in symptomatic pawpaw trees and emphasize the importance of also monitoring non-symptomatic trees. We confirmed graft transmission with 100% transmission rate observed in 200 trees grafted from a TRSV-infected pawpaw (Shenandoah cultivar), and investigation of other transmission vectors is on going. Because of TRSV's wide host range (Tolin, 2008), its broad transmission profile in other crops (via nematodes, thrips, seeds, sap inoculation, and grafting) (Hill and Whitham, 2014), and the notable decline observed in infected pawpaws from different cultivars (10-35, NC-1, Overleese, Pennsylvania-Golden, Shenandoah, Sunflower, Wabash), TRSV appears to pose a new threat to pawpaw orchards. To the best of our knowledge, this is the first report of TRSV infecting pawpaw in North America and the world.

The chestnuts genus (Castanea spp.) is comprised of economically important trees native to the Northern hemisphere that are used as food and hardwood timber. Here, a very efficient method for micropropagation of European × Japanese chestnut hybrids (Castanea sativa × C. crenata) is described. Woody Plant Medium was used as the basal medium. In vitro shoots of four rootstock cultivars were micropropagated without shoot-tip necrosis on multiplication medium containing 5.7 or 11.4 µmol·L−1 zeatin riboside, and were rooted on rooting medium containing 2.46 µmol·L−1 indolebutyric acid. Monthly shoot multiplication rates for each cultivar were 2–5 folds. In vitro rooting percentages for four cultivars were 87% for ‘Maraval’, 67% for ‘Marigoule’, 93% for ‘Marsol’, and 97% for ‘Précoce Migoule’. Within a 5 week period, 80%–95% of rooted shoots were successfully acclimated under high humidity conditions after they were planted in either soil or rockwool.

The quality of potato tubers is dependent on several attributes been maintained at appropriate levels during storage. One of these attributes is sprouting activity that is initiated from meristematic regions of the tubers (eyes). Sprouting activity is a major problem that contributes to reduced shelf life and elevated sugar content, which affects the marketability of seed tubers as well as fried products. This study compared the capabilities of three different optical systems (1: visible/near-infrared (Vis/NIR) interactance spectroscopy, 2: Vis/NIR hyperspectral imaging, 3: NIR transmittance) and machine learning methods to detect sprouting activity in potatoes based on the primordial leaf count (LC). The study was conducted on Frito Lay 1879 and Russet Norkotah cultivars stored at different temperatures and classification models were developed that considered both cultivars combined and classified the tubers as having either high or low sprouting activity. Measurements were performed on whole tubers and sliced samples to see the effect this would have on identifying sprouting activity. Sequential forward selection was applied for wavelength selection and the classification was carried out using K-nearest neighbor, partial least squares discriminant analysis, and soft independent modeling class analogy. The highest classification accuracy values obtained by the hyperspectral imaging system and was 87.5% and 90% for sliced and whole samples, respectively. Data fusion did not show classification improvement for whole tubers, whereas a 7.5% classification accuracy increase was illustrated for sliced samples. By investigating different optical techniques and machine learning methods, this study provides a first step toward developing a handheld optical device for early detection of sprouting activity, enabling advanced aid potato storage management.

Sugar content is one of the most important properties of potato tubers as it directly affects their processing and the final product quality, especially for fried products. In this study, data obtained from spectroscopic (interactance and reflectance) and hyperspectral imaging systems were used individually or fused to develop non-cultivar nor growing season-specific regression and classification models for potato tubers based on glucose and sucrose concentration. Data was acquired over three growing seasons for two potato cultivars. The most influential wavelengths were selected from the imaging systems using interval partial least squares for regression and sequential forward selection for classification. Hyperspectral imaging showed the highest regression performance for glucose with a correlation coefficient (ratio of performance to deviation) or r(RPD) of 91.8(2.41) which increased to 94%(2.91) when the data was fused with the interactance data. The sucrose regression results had the highest accuracy using data obtained from the interactance system with r(RPD) values of 74.5%(1.40) that increased to 84.4%(1.82) when the data was fused with the reflectance data. Classification was performed to identify tubers with either high or low sugar content. Classification performance showed accuracy values as high as 95% for glucose and 80.1% for sucrose using hyperspectral imaging, with no noticeable improvement when data was fused from the other spectroscopic systems. When testing the robustness of the developed models over different seasons, it was found that the regression models had r(RPD) values of 55(1.19)–90.3%(2.34) for glucose and 35.8(1.07)–82.2%(1.29) for sucrose. Results obtained in this study demonstrate the feasibility of developing a rapid monitoring system using multispectral imaging and data fusion methods for online evaluation of potato sugar content.

The sprouting of potato tubers during storage is a significant problem that suppresses obtaining high quality seeds or fried products. In this study, the potential of fusing data obtained from visible (VIS)/near-infrared (NIR) spectroscopic and hyperspectral imaging systems was investigated, to improve the prediction of primordial leaf count as a significant sign for tubers sprouting. Electronic and lab measurements were conducted on whole tubers of Frito Lay 1879 (FL1879) and Russet Norkotah (R.Norkotah) potato cultivars. The interval partial least squares (IPLS) technique was adopted to extract the most effective wavelengths for both systems. Linear regression was utilized using partial least squares regression (PLSR), and the best calibration model was chosen using four-fold cross-validation. Then the prediction models were obtained using separate test data sets. Prediction results were enhanced compared with those obtained from individual systems' models. The values of the correlation coefficient (the ratio between performance to deviation, or r(RPD)) were 0.95(3.01) and 0.9s6(3.55) for FL1879 and R.Norkotah, respectively, which represented a feasible improvement by 6.7%(35.6%) and 24.7%(136.7%) for FL1879 and R.Norkotah, respectively. The proposed study shows the possibility of building a rapid, noninvasive, and accurate system or device that requires minimal or no sample preparation to track the sprouting activity of stored potato tubers.

High undesirable spoilage of peeled chestnuts after thawing prompted a 2006-2007 survey in which chestnuts were quantitatively examined for microbial contaminants after harvest and peeling. Chestnuts (C. sativaxC. crenata cv. Colossal) were collected after harvest from seven Michigan farms, and peeled using a commercial-brulage-peeler. Average mesophilic aerobic bacteria (MAB), yeast and molds populations in peeled chestnuts were 2.70, 2.74 and 2.51 after harvest; 3.46, 3.27 and 2.40 during peeling; and 5.39, 3.09 and <1.70 log CFU/g after peeling, respectively. Two bacteria Rahnella sp., and Curtobacterium sp. and the yeast Candida sp. were the primary causes of spoilage. With the objective of reducing microbial contamination, six postprocessing sanitizer treatments, as well as X-ray irradiation and warm water (65C) were evaluated (18 days of storage at 4C). X-ray irradiation, 3 min immersion in 92 ppm hydrogen dioxide and 65C water were most effective in reducing MAB and yeast.

Impartial classification of Asparagus sections (Asparagus officinalis L), for the purpose of obtaining desired tip to stem pieces ratio in final product, is extremely important to the processing industry. Thus, there is a need to develop a technique that is able to objectively discern between tip and stem pieces, after asparagus has been processed (cut). In this article, a computer vision methodology is proposed to sort asparagus into three classes: tips, mid-stem pieces and bottom-stem pieces. Nine hundred and fifty-five color images from 50 mm length asparagus pieces (cuts) for the three different classes were acquired, using a flat panel scanner. After preprocessing, a total of 1931 color, textural, and geometric features were extracted from each color image. The most relevant features were selected using a sequential forward selection algorithm. Forty-three features were found to be effective in designing a neural-network classifier with a 4-fold cross-validated overall performance accuracy of 90.2% (+/- 2.2%). Results showed that this method is an accurate, reliable, and objective tool to discern between asparagus tips, mid-stem and bottom pieces, and might be applicable to in-line sorting systems. (C) 2016 Elsevier B.V. All rights reserved.

•Computed Tomography (CT) is examined as a tool to classify processing asparagus.•CT detection of tough-fibrous-tissue classification accuracy is 91.2%.•CT fibrous tissue detection in asparagus has potential to sort this quality concern.•Algorithms classifying asparagus internal quality may be suitable for inline systems.

This research was designed to develop and test an automatic image analysis method (algorithm) to classify CT images obtained from 1233 carrot (Daucus carota L) sections (samples), collected during the 2013 and 2014 harvesting seasons. Classification accuracy was evaluated by comparing the classes obtained using eighteen CT images per carrot section to their undesirable fibrous tissue class, based on the industry-simulated invasive quality assessment (% of fiber). Class-0 represents fibrous-free samples, and class-1 denotes samples containing fibrous tissue.After CT image preprocessing, cropping, and segmentation, 3762 grayscale intensity and textural features were extracted from the eighteen CT images per sample. A 4-fold cross-validation linear discriminant classifier with a performance accuracy of 87.9% was developed using 95 relevant features, which were selected using a sequential forward selection algorithm with the Fisher discriminant objective function. This objective method is accurate in determining the presence of undesirable fibrous tissue in pre-processed carrots. (C) 2016 Elsevier Ltd. All rights reserved.

BACKGROUND:Chestnut is a relatively new cultivated crop for Michigan, and postharvest loss due to decay has been problematic as production has increased each year. In 2007, more than 25% of chestnuts were lost to postharvest decay, equivalent to approximately 5300 kg of fresh product. To determine the organisms responsible for decay, a microbiological survey was performed in 2006 and 2007 to identify microorganisms involved in postharvest shell (external surface) mold and internal kernel (edible portion) decay of chestnuts.RESULTS:Filamentous fungi including Penicillium expansum, Penicillium griseofulvum, Penicillium chrysogenum, Coniophora puteana, Acrospeira mirabilis, Botryosphaeria ribis, Sclerotinia sclerotiorum, Botryotinia fuckeliana (anamorph Botrytis cinerea) and Gibberella sp. (anamorph Fusarium sp.) were the predominant microorganisms that negatively impacted fresh chestnuts. Populations of microorganisms varied between farms, harvesting methods and chestnut parts.CONCLUSION:Chestnuts harvested from the orchard floor were significantly (P < 0.05) more contaminated than chestnuts harvested directly from the tree, by more than 2 log colony-forming units (CFU) g(-1) . In addition, a significant difference (P < 0.05) in the microbial population was seen between chestnuts submitted by different growers, with average count ranges of fungi, mesophilic aerobic bacteria (MAB) and yeasts equal to 4.75, 4.59 and 4.75 log CFU g(-1) respectively. © 2016 Society of Chemical Industry.

Near-infrared (NIR) diffuse reflectance has been extensively and successfully applied on quality assurance for fruits, vegetables, and food products. This study is principally aimed to extract the primary wavelengths related to the prediction of glucose and sucrose for potato tubers (of Frito Lay 1879 (FL), a chipping cultivar, and Russet Norkotah (RN), a table use cultivar, and investigating the potential of classification of potatoes based on sugar levels important to the frying industry. Whole tubers, as well as 12.7 mm slices, were scanned using a NIR reflectance spectroscopic system (900-1685 nm). To extract the most influential wavelength in the studied range, interval partial least squares (IPLS), and genetic algorithm (GA) were utilized. Partial least squares regression (PLSR) was applied for building prediction models. Prediction models for RN showed stronger correlation than FL with r(RPD) (correlation coefficient (ratio of reference standard deviation to root mean square error of the model)) values for whole tubers for glucose being as high as 0.81(1.70), and 0.97(3.91) for FL and RN; in the case of sliced samples the values were 0.74(1.49) and 0.94(2.73) for FL and RN. Lower correlation was obtained for sucrose with r(RPD) for whole tubers as high as 0.75(1.52), 0.92(2.57) for FL and RN; and the values for sliced samples were 0.67(1.31) and 0.75(1.41) for FL and RN respectively. Classification of potatoes based on sugar levels was conducted and training models were built using different classifiers (linear discriminant analysis (LDA), K-nearest neighbor (Knn), partial least squares discriminant analysis (PLSDA), and artificial neural network (ANN)), in addition to classifier fusion. To obtain more robust classification models for the training data, 4-fold cross validation was used and results were tested using separate sets of data. Classification rates of the testing set for whole tubers, based on glucose, were as high as 81% and 100% for FL and RN. For sliced samples, the rates were 83% and 81% for FL and RN. Generally, lower classification rates were obtained based on sucrose with values of whole tubers of 71%, and 79% for FL and RN, and for sliced samples the rates were 75%, and 82% which follows a similar trend as PLSR results. This study presents a potential of using selected wavelengths and NIR reflectance spectroscopy to effectively evaluate the sugar content of potatoes and classify potatoes based on thresholds that are crucial for the frying industry. (C) 2015 Elsevier B.V. All rights reserved.

Potato, with its several processed products, has a major rank on the human diet in many countries. Among electronic-based methods that have been used for tracking and rapidly measuring the quality attributes of raw and processed potatoes (more specifically: French fry and chip), and which are reviewed herein, vision and spectroscopic systems have shown the most promising applicability, robustness, and stable performance. Detection of external and internal defects associated with potatoes during harvesting and handling operations has been made possible using nondestructive techniques. Commercial electronic systems used for sorting potato tubers and products are being incorporated into the potato industry and are included and discussed in detail related to operation theories and performance. The need for healthy food requires more attention for detecting harmful chemicals in fried products such as acrylamide which itself demands continuous tracking of sugar during storage and in French fries or chips which encourages the need for constitute-based sorting for potatoes. Hyperspectral imaging is one of the most recently emerging tools and provides advantages of vision and spectroscopic systems and can be used, after speeding up image acquisition time, in prediction of processing-related constituents as well as defects detection. Moreover other noninvasive techniques, such as NMR and X-ray CT, have shown the potential for successful application in quality monitoring of fruits and vegetables with expected possibility for application in potatoes.

This research was designed to investigate the presence of undesirable fibrous tissue in carrots through Computed Tomography (CT) images. Also, the structural polymers content (cellulose, hemicellulose and lignin) of different types of fibrous tissue, fibrous-free and fibrous carrots were determined by a laboratory analytical procedure (National Renewable Energy Laboratory standards). CT scans were performed on 224 fresh carrots, containing varying undesirable fibrous tissue levels, using a GE-BrightSpeed (R) RT-Elite CT system (Buckinghamshire, UK). Two-dimensional (2D) CT images were acquired every 2.5 mm, at a voltage and current equal to 120 kV and 240 mA, respectively. Houns-field-Unit (HU) values (tissue physical densities) were extracted from different 2D CT image regions from dissimilar carrot components (phloem, xylem and vascular cambium), in fibrous and fibrous-free carrots. A significant decrease (P < 0.05) in HU values and a significant increase (P < 0.05) in structural polymers was observed when carrot undesirable fibrous tissue was present. (C) 2014 Elsevier Ltd. All rights reserved.

Computer tomography (CT) imaging is an effective method for in vivo characterization of object internal attributes including fresh agro-food product quality. Limitations to move CT technology forward into the development of an inline system include the lack of standardized tools (phantoms) for image quality analysis, cross-sharing, and consistent evaluation. The objective of this study was to develop a set of agarose phantoms suitable for detection of pit and pit fragments using CT imaging. Efficiently sorting out these undesirable features during handling and processing will be extremely beneficial to the tart cherry industry. These phantoms can be used on several CT devices (including ultra-fast CT systems) to quantify CT performance, reproducibility, and applicability. This article describes how the phantoms were created, using agarose, a broadly available and inexpensive material. Developed phantoms allow for the measurement of CT image parameters that are relevant to detect fresh cherry pits and/or pit fragments and helps in the development of inline CT equipment. Measured phantom CT image parameters include simulated flesh and embedded pit X-ray CT attenuation properties (HU-values), which are statistically similar (p = 0.05) to fresh tart cherries. In addition, using CT images, pit and pit fragment size can be inferred with a high accuracy rate (R = 0.99, p value <0.01).

Visible/near-infrared (VIS/NIR) hyperspectral reflectance imaging was evaluated as a technique toward rapid prediction of the glucose and sucrose percentages in two common fresh use and chipping potato cultivars. Tubers were sampled and held in multiple storage temperatures in an attempt to develop uniform and broad constituent distributions. Each tested sample was a 12.7-mm-thick slice cut uniformly from all tubers. Multiple features were extracted from samples including mean reflectance spectra and curve feature parameters yielded from an exponential model. Both glucose and sucrose ratios were measured using the Megazyme sucrose/ D -glucose assay procedure as reference values. Partial least squares regression (PLSR), feed forward neural networks (FFNN), radial basis functions neural networks (RBFNN), and exact design radial basis functions (RBFNNE) neural networks were used for building calibration and prediction models. PLSR results demonstrated strongly correlated models built using mean reflectance spectra for glucose for Russet Norkotah (RN) with R (RPD) (or correlation coefficient (ratio of sample standard deviation to standard error of prediction)) values as high as 0.97 (3.58), whereas those values were 0.81 (1.70) for Frito Lay 1879 (FL). Sucrose models showed less correlation performance with R (RPD) values as high as 0.60 (1.14) for FL and 0.38 (1.00) for RN. Wavelength selection/prediction using interval partial least squares (IPLS) and genetic algorithm (GA) was conducted on the data, and PLSR and NN results were close to the full-wavelength models for the glucose and sucrose of both cultivars with a preference given to IPLS as it yields less selected variables than GA. Applying K-nearest neighbor (Knn) and partial least squares discriminant analysis (PLSDA) on mean reflectance spectra resulted in glucose misclassification errors of 14 % and 18 % for FL and RN, respectively. However, classification errors were higher for sucrose indicating lower accuracy for this sugar (34 and 30 % for FL and RN). The results in this study give promise to the possibility of measuring each of these sugars rapidly for quality control and monitoring in the potato industry.

Near-infrared (NIR) transmittance spectroscopy, visible/NIR interactance spectroscopy, and visible/NIR hyperspectral imaging modes were used to determine the potential for rapid electronic estimation of glucose, sucrose, specific gravity, primordial leaf count, and soluble solids of (FL) (chipping) and Russet Norkotah (RN) (table) potato cultivars. Whole tubers and 0.5 inch (12.54 mm) slices were evaluated. Partial least squares regression (PLSR) was used to obtain the prediction models. Models for leaf counts and glucose were promising for all modes with the optimum model obtained for leaf count from interactance with sliced samples resulting in R (RPD) values of 0.95(3.29) for FL, and 0.90(2.19) for RN. For glucose, interactance also yielded the best model with R (RPD) values of 0.90(2.14) for FL, and 0.95(3.12) for RN. Models of other constituents were inconsistent between systems. Interactance mode with sliced samples showed best performance for soluble solids for FL with R (RPD) values of 0.55(1.18). Also, interactance mode demonstrated optimal performance for sucrose estimation with R (RPD) values of 0.81(1.63) for FL obtained from sliced samples, and 0.81(1.64) from whole tubers. Transmittance mode with sliced samples showed the best prediction models for RN with R (RPD) values of 0.63(1.30) for sucrose. Finally, specific gravity under interactance and transmittance modes with sliced samples for FL and RN respectively yielded R (RPD) values of 0.61(1.27), and 0.59(1.22). (C) 2014 Elsevierer Ltd. All rights reserved.