Browsing by Author "Miguel Aguilera, Jose"

Now showing 1 - 7 of 7
  • Thumbnail Image
    Item
    Automated fish bone detection using X-ray imaging
    (ELSEVIER SCI LTD, 2011) Mery, Domingo; Lillo, Ivan; Loebel, Hans; Riffo, Vladimir; Soto, Alvaro; Cipriano, Aldo; Miguel Aguilera, Jose
    In countries where fish is often consumed, fish bones are some of the most frequently ingested foreign bodies encountered in foods. In the production of fish fillets, fish bone detection is performed by human inspection using their sense of touch and vision which can lead to misclassification. Effective detection of fish bones in the quality control process would help avoid this problem. For this reason, an X-ray machine vision approach to automatically detect fish bones in fish fillets was developed. This paper describes our approach and the corresponding experiments with salmon and trout fillets. In the experiments, salmon X-ray images using 10 x 10 pixels detection windows and 24 intensity features (selected from 279 features) were analyzed. The methodology was validated using representative fish bones and trouts provided by a salmon industry and yielded a detection performance of 99%. We believe that the proposed approach opens new possibilities in the field of automated visual inspection of salmon, trout and other similar fish. (C) 2011 Elsevier Ltd. All rights reserved.
  • Thumbnail Image
    Item
    Description of the kinetic enzymatic browning in banana (Musa cavendish) slices using non-uniform color information from digital images
    (ELSEVIER, 2009) Quevedo, Roberto; Diaz, Oscar; Ronceros, Betty; Pedreschi, Franco; Miguel Aguilera, Jose
    A novel methodology "fractal browning indicator" (FBI) is presented, that describes the enzymatic browning kinetic based on the use of irregular color patterns from banana slice images. It uses the fractal Fourier texture image value in a selected area, to calculate a fractal dimension (FD), which represents the complexity of color distribution. During the procedure, colors from digital images were first transformed to L*a*b* space color using a transformation function (quadratic model), in order to derivate three color channels, lightness (L*), redness (a*), and yellowness (b*). In the results, lightness and yellowness parameters decreased during the browning kinetic, when their respective FD values increased, indicating major color distribution complexity in a selected area analyzed during the kinetic. The redness color (a*) did not show any statistical variation. The empirical power law model was suitable to correlate enzymatic browning kinetic data both for FBI and for the traditional method (when an L* mean was used). However, enzymatic browning rates using the FBI method, were between 8.5 and 35 times higher than rates calculated with the traditional method. (C) 2009 Elsevier Ltd. All rights reserved.
  • Thumbnail Image
    Item
    Effect of guar gum content on some physical and nutritional properties of extruded products
    (ELSEVIER SCI LTD, 2011) Parada, Javier; Miguel Aguilera, Jose; Brennan, Charles
    The effect of guar gum (0-10%) added to flour (maize, potato, rice, and wheat) prior to extrusion on the microstructure, physical properties (texture, expansion, density, pasting) and nutritional properties (starch digestibility) was investigated. The inclusion of guar gum did not decrease starch digestibility; rather, at 10% guar gum rapidly digestible starch increased by 24%, 15%, 25% and 43%, in maize, potato, rice and wheat flour-based products, respectively. In general, increases in starch digestibility appear to be related to the weaker microstructure (i.e., lower textural hardness), larger matrix surface area, and lower viscosity (pasting properties) of extrudates containing guar gum. These results suggest that microstructural changes affect the starch digestibility of extrudates; nevertheless, probably other factors such as particle size during digestion may also play an important role. (C) 2010 Elsevier Ltd. All rights reserved.
  • Thumbnail Image
    Item
    Fabrication, characterization and lipase digestibility of food-grade nanoemulsions
    (ELSEVIER SCI LTD, 2012) Troncoso, Elizabeth; Miguel Aguilera, Jose; McClements, David Julian
    The behavior of nanoemulsion-based delivery systems within the gastrointestinal tract determines their functional performance. In this study, the influence of particle radius (30-85 nm) on the in vitro digestion of nanoemulsions containing non-ionic surfactant stabilized lipid (corn oil) droplets was examined using simulated small intestine conditions. Nanoemulsions were prepared by a combination of high-pressure homogenization and solvent (hexane) displacement. Lipid droplets with different sizes were prepared by varying the oil-to-solvent ratio in the disperse phase prior to homogenization. The fraction of free fatty acids (FFA) released from emulsified triacylglycerols (TG) during digestion was measured by an in vitro model (pH-Stat titration). Nanoemulsions exhibited a lag-period before any FFA were released, which was explained by inhibition of lipase adsorption to the oil-water interface by free surfactant. After the lag-period, the digestion rate increased with decreasing oil droplet diameter (increasing specific surface area). The total amount of FFA released from the emulsions increased from 61% to 71% as the mean droplet radius decreased from 86 nm to 30 nm. The incomplete digestion of the emulsified lipids could be explained by inhibition of lipase activity by the release of fatty acids and/or by interactions between lipase and surfactants molecules. (C) 2011 Elsevier Ltd. All rights reserved.
  • Thumbnail Image
    Item
    Influence of particle size on the in vitro digestibility of protein-coated lipid nanoparticles
    (ACADEMIC PRESS INC ELSEVIER SCIENCE, 2012) Troncoso, Elizabeth; Miguel Aguilera, Jose; McClements, David Julian
    The influence of particle size on the in vitro digestion of beta-lactoglobulin (BLG)-coated lipid nanoparticles was examined using simulated small intestine conditions. Nanoemulsions were prepared by high-pressure homogenization and organic solvent (hexane) evaporation. The effect of the initial organic phase composition on the size, microstructure, electrical properties, and digestion of the lipid nanoparticles was evaluated. The radius of the nanoparticles decreased (from 85 to 48 nm) as the solvent concentration in the initial organic phase increased (from 0% to 95%). The lipid digestion rate initially decreased with decreasing particle radius (for r = 85-59 nm), but then it increased (for r = 59-48 nm). This dependence is contrary to the usual assumption that lipid digestion increases with increasing lipid surface area. Our results suggest that the structure of the protein layer coating the lipid nanoparticles has an important effect on lipid digestion. (C) 2012 Elsevier Inc. All rights reserved.
  • Thumbnail Image
    Item
    Quality classification of corn tortillas using computer vision
    (ELSEVIER SCI LTD, 2010) Mery, Domingo; Chanona Perez, Jorge J.; Soto, Alvaro; Miguel Aguilera, Jose; Cipriano, Aldo; Velez Rivera, Nayeli; Arzate Vazquez, Israel; Gutierrez Lopez, Gustavo F.
    Computer vision is playing an increasingly important role in automated visual food inspection. However, quality control in tortilla production is still performed by human operators which may lead to misclassification due to their subjectivity and fatigue. In order to reduce the need for human operators and therefore misclassification, we developed a computer vision framework to automatically classify the quality of corn tortillas according to five hedonic sub-classes given by a sensorial panel. The proposed framework analyzed 750 corn tortillas obtained from 15 different Mexican commercial stores which were either small, medium or large in size. More than 2300 geometric and color features were extracted from 1500 images capturing both sides of the 750 tortillas. After implementing a feature selection algorithm, in which the most relevant features were selected for the classification of the five sub-classes, only 64 features were required to design a classifier based on support vector machines. Cross-validation yielded a performance of 95% in the classification of the five hedonic sub-classes. Additionally, using only 10 of the selected features and a simple statistical classifier, it was possible to determine the origin of the tortillas with a performance of 96%. We believe that the proposed framework opens up new possibilities in the field of automated visual inspection of tortillas. (c) 2010 Elsevier Ltd. All rights reserved.
  • Thumbnail Image
    Item
    Quantification of enzymatic browning in apple slices applying the fractal texture Fourier image
    (ELSEVIER SCI LTD, 2009) Quevedo, Roberto; Jaramillo, Marcela; Diaz, Oscar; Pedreschi, Franco; Miguel Aguilera, Jose
    A new approach (FBI) describing the enzymatic browning kinetics for three apple cultivars, is presented. It is based on quantification of the irregular color patterns that emerge from the apple surface during enzymatic browning, rather than using the color average in the same area analyzed. In the experiments, three apple cultivars slices were placed under a computer vision system and color digital images were captured. The images were transformed to Lab space color using a quadratic transformation function and the Fourier fractal texture image was used to calculate a fractal dimension value (FD), in order to represent the complexity of lightness intensity distribution (L) over the surface. FD (proposed method) and the mean L value (traditional method) were used indistinctly (as a fractional conversion) to model the enzymatic kinetic using the power-law model. The results showed that the fractal theory can be used to describe the browning kinetic and to distinguish apple cultivars, based on their browning sensitivity under the same experimental conditions. Enzymatic browning rates derived using the fractal kinetic method, were between 14.3 and 23.2 times (in absolute value) higher than the rates calculated with the traditional method. The fractional first-order model was established only for kinetics calculated using the traditional method. (c) 2009 Elsevier Ltd. All rights reserved.