Pilar Barreiro

Grapevine Yield and Leaf Area Estimation Using Supervised Classification Methodology on RGB Images Taken under Field Conditions

The aim of this research was to implement a methodology through the generation of a supervised classifier based on the Mahalanobis distance to characterize the grapevine canopy and assess leaf area and yield using RGB images. The method automatically processes sets of images, and calculates the areas (number of pixels) corresponding to seven different classes (Grapes, Wood, Background, and four classes of Leaf, of increasing leaf age). Each one is initialized by the user, who selects a set of representative pixels for every class in order to induce the clustering around them. The proposed methodology was evaluated with 70 grapevine (V. vinifera L. cv. Tempranillo) images, acquired in a commercial vineyard located in La Rioja (Spain), after several defoliation and de-fruiting events on 10 vines, with a conventional RGB camera and no artificial illumination. The segmentation results showed a performance of 92% for leaves and 98% for clusters, and allowed to assess the grapevine’s leaf area and yield with R2 values of 0.81 (p < 0.001) and 0.73 (p = 0.002), respectively. This methodology, which operates with a simple image acquisition setup and guarantees the right number and kind of pixel classes, has shown to be suitable and robust enough to provide valuable information for vineyard management.

Prospects for the rapid detection of mealiness in apples by nondestructive NMR relaxometry

The potential of nuclear magnetic resonance (NMR) relaxometry for quantitative evaluation of apple mealiness has been investigated. The degree of “mealiness” was defined by several mechanical techniques, including penetration, compression and shear rupture as well as by the BRIX (soluble solids) and juiciness levels. These data were correlated with both magnetic resonance imaging (MRI) and NMR water proton transverse relaxation time measurements on a fruit-by-fruit basis. It was found that increasing mealiness caused a systematic increase in the transverse relaxation rate. The potential for rapid, on-line NMR/MRI detection of apple mealiness is discussed.

Detection of Freeze Injury in Oranges by Magnetic Resonance Imaging of Moving Samples

Magnetic resonance imaging (MRI) is applied for on-line inspection of fruits. The aim of this work is to address the applicability of MRI for freeze injury detection in oranges directly on a distribution chain. Undamaged and damaged oranges are conveyed at 50 and 100 mm/s by a specially designed conveyor within a 4.7 T spectrometer obtaining fast low-angle shot images. An automatic segmentation algorithm is proposed that allows the discrimination between undamaged and damaged oranges.

Computer-assisted enhanced volumetric segmentation magnetic resonance imaging data using a mixture of artificial neural networks.

An accurate computer-assisted method able to perform regional segmentation on 3D single modality images and measure its volume is designed using a mixture of unsupervised and supervised artificial neural networks. Firstly, an unsupervised artificial neural network is used to estimate representative textures that appear in the images. The region of interest of the resultant images is selected by means of a multi-layer perceptron after a training using a single sample slice, which contains a central portion of the 3D region of interest. The method was applied to magnetic resonance imaging data collected from an experimental acute inflammatory model (T(2) weighted) and from a clinical study of human Alzheimers disease (T(1) weighted) to evaluate the proposed method. In the first case, a high correlation and parallelism was registered between the volumetric measurements, of the injured and healthy tissue, by the proposed method with respect to the manual measurements (r = 0.82 and p < 0.05) and to the histopathological studies (r = 0.87 and p < 0.05). The method was also applied to the clinical studies, and similar results were derived of the manual and semi-automatic volumetric measurement of both hippocampus and the corpus callosum (0.95 and 0.88).

Detection and Quantification of Peanut Traces in Wheat Flour by near Infrared Hyperspectral Imaging Spectroscopy Using Principal-Component Analysis:

The use of a common environment for processing different powder foods in the industry has increased the risk of finding peanut traces in powder foods. The analytical methods commonly used for detection of peanut such as enzyme-linked immunosorbent assay (ELISA) and real-time polymerase chain reaction (RT-PCR) represent high specificity and sensitivity but are destructive and time-consuming, and require highly skilled experimenters. The feasibility of NIR hyperspectral imaging (HSI) is studied for the detection of peanut traces down to 0.01% by weight. A principal-component analysis (PCA) was carried out on a dataset of peanut and flour spectra. The obtained loadings were applied to the HSI images of adulterated wheat flour samples with peanut traces. As a result, HSI images were reduced to score images with enhanced contrast between peanut and flour particles. Finally, a threshold was fixed in score images to obtain a binary classification image, and the percentage of peanut adulteration was compared with the percentage of pixels identified as peanut particles. This study allowed the detection of traces of peanut down to 0.01% and quantification of peanut adulteration from 10% to 0.1% with a coefficient of determination (r2) of 0.946. These results show the feasibility of using HSI systems for the detection of peanut traces in conjunction with chemical procedures, such as RT-PCR and ELISA to facilitate enhanced quality-control surveillance on food-product processing lines.

Neural bruise prediction models for fruit handling and machinery evaluation

Abstract Neural bruise prediction models based on the degree of fruit damage of the most traded fruit species and varieties were developed for prediction of the fruits to be accepted or rejected. The prediction relied on European Community standards. Different models for both quasi-static (compression) and dynamic (impact) loads covering the full commercial ripening period of fruits were developed. A simulation process was developed for gathering the information on laboratory bruise models and load sensor calibrations for different electronic devices (IS-100 and DEA-1, for impact and compression loads, respectively). An evaluation method was also designed for acquiring and gathering the information on the mechanical properties of fruits and the loading records of the electronic devices. The evaluation system allowed for determination of the current stage of fruit handling processes and machinery.

Interpolation of spatial temperature profiles by sensor networks

The monitoring of spatial profiles of a physical property such as temperature becomes feasible with the decreasing cost of wireless sensor nodes. But to obtain a temperature value for each point in space, it is necessary to interpolate between the existing sensor positions. Accurate spatial temperature supervision is a crucial precondition for maintaining high quality standards in the transportation of food products. The Kriging method was programmed for the ARM processor of the iMote2 sensor nodes and tested with 14 experimental data sets that were recorded in cold storage rooms and transports in trucks and containers. The error of the interpolation by Kriging was 20% lower than the simpler inverse-distance-weighting used as a reference method.

Feature extraction on vineyard by Gustafson Kessel FCM and K-means

Image segmentation is a process by which an image is partitioned into regions with similar features. Many approaches have been proposed for color images segmentation, but Fuzzy C-Means has been widely used, because it has a good performance in a wide class of images. However, it is not adequate for noisy images and it takes longer runtimes, as compared to other method like K-means. For this reason, several methods have been proposed to improve these weaknesses. Methods like Fuzzy C-Means with Gustafson-Kessel algorithm (FCM-GK), which improve its performance against the noise, but increase significantly the runtime. In this paper we propose to use the centroids generated by GK-FCM algorithms as seeding for K-means algorithm in order to accelerate the runtime and improve the performance of K-means with random seeding. These segmentation techniques were applied to feature extraction on vineyard images. Segmented images were evaluated using several quality parameters such as the rate of correctly classified area and runtime.

Undergraduate Design Experiences in the Trans-Atlantic Biosystems Engineering Network (TABE.NET)

A Trans-Atlantic Biosystems Engineering Network (TABE.NET) has been established with the overall goal to advance internationalization of Biosystems Engineering (BSEN) curricula and develop a global awareness within the discipline. The participating institutions are Virginia Polytechnic Institute and State University (VT), University of Illinois at Urbana-Champaign (UIUC), University College Dublin (UCD), Agricultural University of Athens (AUA), Universidad Politecnica de Madrid (UPM), and University of Bari (UniBar). A working group is exploring the potential to develop an international collaborative design project for undergraduate students in the participating institutions. This paper summarizes the first step in the process by examining current course structures and design experiences across the network.

Quantitative analysis of morphological changes in yeast colonies growing on solid medium: the eccentricity and Fourier indices

The colony shape of four yeast species growing on agar medium was measured for 116 days by image analysis. Initially, all the colonies are circular, with regular edges. The loss of circularity can be quantitatively estimated by the eccentricity index, Ei, calculated as the ratio between their orthogonal vertical and horizontal diameters. Ei can increase from 1 (complete circularity) to a maximum of 1.17–1.30, depending on the species. One colony inhibits its neighbour only when it has reached a threshold area. Then, Ei of the inhibited colony increases proportionally to the area of the inhibitory colony. The initial distance between colonies affects those threshold values but not the proportionality, Ei/area; this inhibition affects the shape but not the total surface of the colony. The appearance of irregularities in the edges is associated, in all the species, not with age but with nutrient exhaustion. The edge irregularity can be quantified by the Fourier index, Fi, calculated by the minimum number of Fourier coefficients that are needed to describe the colony contour with 99% fitness. An ad hoc function has been developed in Matlab v. 7.0 to automate the computation of the Fourier coefficients. In young colonies, Fi has a value between 2 (circumference) and 3 (ellipse). These values are maintained in mature colonies of Debaryomyces, but can reach values up to 14 in Saccharomyces. All the species studied showed the inhibition of growth in facing colony edges, but only three species showed edge irregularities associated with substrate exhaustion. Copyright