RafanoSet: Dataset of raw, manually, and automatically annotated Raphanus Raphanistrum weed images for object detection and segmentation.

The rationale for this data article is to provide resources which could facilitate the studies focussed over weed detection and segmentation in precision farming using computer vision. We have curated Multispectral (MS) images over crop fields of Triticum Aestivum containing heterogenous mix of Raphanus raphanistrum in both uniform and random crop spacing. This dataset is designed to facilitate weed detection and segmentation based on manual and automatically annotated Raphanus raphanistrum, commonly known as wild radish. The dataset is publicly available through the Zenodo data library and provides annotated pixel-level information that is crucial for registration and segmentation purposes. The dataset consists of 85 original MS images captured over 17 scenes covering various spectra including Blue, Green, Red, NIR (Near-Infrared), and RedEdge. Each image has a dimension of 1280 × 960 pixels and serves as the basis for the specific weed detection and segmentation. Manual annotations were performed using Visual Geometry Group Image Annotator (VIA) and the results were saved in Common Objects in Context (COCO) segmentation format. To facilitate this resource-intensive task of annotation, a Grounding DINO + Segment Anything Model (SAM) was trained with this manually annotated data to obtain automated Visual Object Classes Extended Markup Language (PASCAL VOC) annotations for 80 MS images. The dataset emphasizes quality control, validating both the 'manual" and 'automated" repositories by extracting and evaluating binary masks. The codes used for these processes are accessible to ensure transparency and reproducibility. This dataset is the first-of-its-kind public resource providing manual and automatically annotated weed information over close-ranged MS images in heterogenous agriculture environment. Researchers and practitioners in the fields of precision agriculture and computer vision can use this dataset to improve MS image registration and segmentation at close range photogrammetry with a focus on wild radish. The dataset not only helps with intra-subject registration to improve segmentation accuracy, but also provides valuable spectral information for training and refining machine learning models.

GobhiSet: Dataset of raw, manually, and automatically annotated RGB images across phenology of Brassica oleracea var. Botrytis.

This research introduces an extensive dataset of unprocessed aerial RGB images and orthomosaics of Brassica oleracea crops, captured via a DJI Phantom 4. The dataset, publicly accessible, comprises 244 raw RGB images, acquired over six distinct dates in October and November of 2020 as well as 6 orthomosaics from an experimental farm located in Portici, Italy. The images, uniformly distributed across crop spaces, have undergone both manual and automatic annotations, to facilitate the detection, segmentation, and growth modelling of crops. Manual annotations were performed using bounding boxes via the Visual Geometry Group Image Annotator (VIA) and exported in the Common Objects in Context (COCO) segmentation format. The automated annotations were generated using a framework of Grounding DINO + Segment Anything Model (SAM) facilitated by YOLOv8x-seg pretrained weights obtained after training manually annotated images dated 8 October, 21 October, and 29 October 2020. The automated annotations were archived in Pascal Visual Object Classes (PASCAL VOC) format. Seven classes, designated as Row 1 through Row 7, have been identified for crop labelling. Additional attributes such as individual crop ID and the repetitiveness of individual crop specimens are delineated in the Comma Separated Values (CSV) version of the manual annotation. This dataset not only furnishes annotation information but also assists in the refinement of various machine learning models, thereby contributing significantly to the field of smart agriculture. The transparency and reproducibility of the processes are ensured by making the utilized codes accessible. This research marks a significant stride in leveraging technology for vision-based crop growth monitoring.

Comprehensive Evaluation of Multispectral Image Registration Strategies in Heterogenous Agriculture Environment.

This article is focused on the comprehensive evaluation of alleyways to scale-invariant feature transform (SIFT) and random sample consensus (RANSAC) based multispectral (MS) image registration. In this paper, the idea is to extensively evaluate three such SIFT- and RANSAC-based registration approaches over a heterogenous mix containing Triticum aestivum crop and Raphanus raphanistrum weed. The first method is based on the application of a homography matrix, derived during the registration of MS images on spatial coordinates of individual annotations to achieve spatial realignment. The second method is based on the registration of binary masks derived from the ground truth of individual spectral channels. The third method is based on the registration of only the masked pixels of interest across the respective spectral channels. It was found that the MS image registration technique based on the registration of binary masks derived from the manually segmented images exhibited the highest accuracy, followed by the technique involving registration of masked pixels, and lastly, registration based on the spatial realignment of annotations. Among automatically segmented images, the technique based on the registration of automatically predicted mask instances exhibited higher accuracy than the technique based on the registration of masked pixels. In the ground truth images, the annotations performed through the near-infrared channel were found to have a higher accuracy, followed by green, blue, and red spectral channels. Among the automatically segmented images, the accuracy of the blue channel was observed to exhibit a higher accuracy, followed by the green, near-infrared, and red channels. At the individual instance level, the registration based on binary masks depicted the highest accuracy in the green channel, followed by the method based on the registration of masked pixels in the red channel, and lastly, the method based on the spatial realignment of annotations in the green channel. The instance detection of wild radish with YOLOv8l-seg was observed at a mAP@0.5 of 92.11% and a segmentation accuracy of 98% towards segmenting its binary mask instances.

Computer-aided food engineering.

Computer-aided food engineering (CAFE) can reduce resource use in product, process and equipment development, improve time-to-market performance, and drive high-level innovation in food safety and quality. Yet, CAFE is challenged by the complexity and variability of food composition and structure, by the transformations food undergoes during processing and the limited availability of comprehensive mechanistic frameworks describing those transformations. Here we introduce frameworks to model food processes and predict physiochemical properties that will accelerate CAFE. We review how investments in open access, such as code sharing, and capacity-building through specialized courses could facilitate the use of CAFE in the transformation already underway in digital food systems.

Particle size and variety of coffee used as variables in mitigation of furan and 2-methylfuran content in espresso coffee.

In this study, the concentration of furan and 2-methylfuran in espresso coffee (EC) obtained from Arabica and Robusta coffee varieties was determined as a function of specific particle size. The particle size and coffee variety significantly influenced the level of furan and 2-methylfuran. In Arabica variety, furan and 2-methylfuran level increased with increasing particle size. Particularly, from C<200µm to C>425µm fractions, furan increased from 68.27 to 91.48 ng mL-1 while 2-methylfuran from 404.31 to 634.64 ng mL-1. In Robusta variety, the highest concentration of furan and 2-methylfuran occurred in ECs prepared using C300-425µm fraction showing values of 116.39 ng mL-1 and 845.14 ng mL-1, respectively, for furan and 2-methylfuran. On the basis of this experiment, it is possible to establish a mitigation strategy by manipulating the particle size and coffee variety in order to reduce the level of furan and 2-methylfuran in EC up to 11.4% and 18.8%, respectively.

Modelling Processes and Products in the Cereal Chain.

In recent years, modelling techniques have become more frequently adopted in the field of food processing, especially for cereal-based products, which are among the most consumed foods in the world. Predictive models and simulations make it possible to explore new approaches and optimize proceedings, potentially helping companies reduce costs and limit carbon emissions. Nevertheless, as the different phases of the food processing chain are highly specialized, advances in modelling are often unknown outside of a single domain, and models rarely take into account more than one step. This paper introduces the first high-level overview of modelling techniques employed in different parts of the cereal supply chain, from farming to storage, from drying to milling, from processing to consumption. This review, issued from a networking project including researchers from over 30 different countries, aims at presenting the current state of the art in each domain, showing common trends and synergies, to finally suggest promising future venues for research.

Processing effects on acrylamide content in roasted coffee production.

Acrylamide is a toxic compound that develops during the roasting process of coffee beans. According to literature, the levels of acrylamide in coffee vary with the percentage of Robusta type in the mix and with the time-temperature parameters during the roasting process. Therefore, this study aimed to find the best roasting conditions in order to mitigate acrylamide formation. Two types of roasted coffee (Arabica and Robusta) were analyzed through GC-MS and two clean-up methods were compared. The best roasting conditions were optimized on an industrial scale and the median levels of acrylamide decreased from the range 170-484 µg kg-1 to 159-351 µg kg-1, after the optimization of roasting parameters. Therefore, the choice of the best conditions, according to the percentage of Robusta type in the finished product, could be an efficient mitigation strategy for acrylamide formation in coffee, maintaining the manufacturer's requirements of the finished product.

Espresso coffee design based on non-monotonic granulometric distribution of aromatic profile.

Coffee beverages may be obtained using several extraction methods, among which espresso coffee (EC) represents now a worldwide adopted system. Recent advances in coffee grinding equipment allow today to achieve a detailed control of granulometric distribution, and the grinding process is an essential step of coffee production cycle both for the aromatic profile composition and for the chemical properties of the beverage (Severini, 2015). The comminution process consists of the breaking down particles into smaller fragments; as well-known, its main objective is to increase the overall particle surface area exposed to water leading to a more efficient extraction of soluble substances (Illy, 2005a). Basically, the coffee brewing process includes two steps: a washing phase concerning the snapshot dissolution of free solubles at the particle surface followed by diffusion phase of solubles within the porous particles (Spiro 1992, Baggenstoss 2008). The variability in particle size distribution on the quality of EC has been studied by various authors. Severini et al. has tackled the influence of the grinding level on the aromatic profiles and chemical attributes (percolation time, caffeine content, pH and titratable acidity) as a consequence of changes in the microstructural properties of the coffee cake. Generally speaking such results would imply that the final effect in terms of aromatic compounds extraction follows a monotonic law respect to granulometric size. This result is true in an average sense but it cannot be given for granted for any aromatic compounds if we refine the resolution of granulometric class. The reasons for which some aromatic compounds do not follow the supposed trend (the lower the grain size, the higher the aromatic compound content) can be most probably related to the internal distribution of precursors and to the different non-isotropic roasting grade of the bean, where the external part undergoes to an increased thermal load. This will change at the same time the kinetics and formation of aromatic compounds, and the mechanical properties as well, strictly correlated to the way the bean is crashed during the grinding phase and consequently to the granulometric distribution of different parts of the coffee bean. Results presented in this work allow to correlate choices in terms of granulometric distribution to characteristics aromatic compounds, in order to enhance specific flavors in espresso coffee.

Characterisation, in vitro digestibility and expected glycemic index of commercial starches as uncooked ingredients.

In this study native starches as ingredients (corn, rice, wheat, tapioca and potato) were characterized for microstructure, physicochemical, functional and thermal properties, in vitro digestibility and glycemic index. There was a significant variation in the granule shape and size distribution of the starches. Particle size monomodal (corn, tapioca, potato) and bimodal (rice, wheat) distribution was observed amongst the starches. The potato starch showed the biggest size granules while the rice showed the smallest. The examined properties and nutritional characteristics of starches were significantly different. Thermal properties were studied using Differential Scanning Calorimeter (DSC). DSC results showed that the transition temperatures (58.8-78.7 °C) and enthalpies of gelatinization (2.3-8.2 J/g) of the starches appeared to be greatly influenced by microstructure and chemical composition (e.g. resistant starch). Nutritional properties such as slowly digestible starch and expected glycemic index values followed the order: rice > wheat > tapioca > corn > potato. In particular, the highest resistant starch was recorded for potato starch.