Automated fish bone detection using X-ray imaging

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 × 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.     

Color measurement in Lab units from RGB digital images

The superficial appearance and color of food are the first parameters of quality evaluated by consumers, and are thus critical factors for acceptance of the food item by the consumer. Although there are different color spaces, the most used of these in the measuring of color in food is the L^*a^*b^* color space due to the uniform distribution of colors, and because it is very close to human perception of color. In order to carry out a digital image analysis in food, it is necessary to know the color measure of each pixel on the surface of the food item. However, there are at present no commercial L^*a^*b^* color measures in pixels available because the existing commercial colorimeters generally measure small, non-representative areas of a few square centimeters. Given that RGB digital cameras obtain information in pixels, this article presents a computational solution that allows the obtaining of digital images in L^*a^*b^* color units for each pixel of the digital RGB image. This investigation presents five models for the RGB → L^*a^*b^* conversion and these are: linear, quadratic, gamma, direct, and neural network. Additionally, a method is suggested for estimating the parameters of the models based on a minimization of the mean absolute error between the color measurements obtained by the models, and by a commercial colorimeter for uniform and homogenous surfaces. In the evaluation of the performance of the models, the neural network model stands out with an error of only 0.93%. On the basis of the construction of these models, it is possible to find a L^*a^*b^* color measuring system that is appropriate for an accurate, exacting and detailed characterization of a food item, thus improving quality control and providing a highly useful tool for the food industry based on a color digital camera.     

Automated Design of a Computer Vision System for Visual Food Quality Evaluation

Considerable research efforts in computer vision applied to food quality evaluation have been developed in the last years; however, they have been concentrated on using or developing tailored methods based on visual features that are able to solve a specific task. Nevertheless, today’s computer capabilities are giving us new ways to solve complex computer vision problems. In particular, a new paradigm on machine learning techniques has emerged posing the task of recognizing visual patterns as a search problem based on training data and a hypothesis space composed by visual features and suitable classifiers. Furthermore, now we are able to extract, process, and test in the same time more image features and classifiers than before. Thus, we propose a general framework that designs a computer vision system automatically, i.e., it finds—without human interaction—the features and the classifiers for a given application avoiding the classical trial and error framework commonly used by human designers. The key idea of the proposed framework is to select—automatically—from a large set of features and a bank of classifiers those features and classifiers that achieve the highest performance. We tested our framework on eight different food quality evaluation problems yielding a classification performance of 95 % or more in every case. The proposed framework was implemented as a Matlab Toolbox available for noncommercial purposes.     

Quality classification of corn tortillas using computer vision

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.     

Cell cycle dependent toxicity of an amphiphilic synthetic peptide

Use of the Internet for multimedia conferencing began in the early 1990s. Multimedia conferencing allows people at multiple, distributed locations to communicate using audio, video and shared workspace programs; the Multicast Backbone of the Internet (MBONE) provides the technical solution to make the most efficient use of the limited Internet bandwidth for such interactions. The scope for using this technology in medical applications was recognised by the MICE project which, in November 1994, used Sun SPARC workstations connected to the MBONE to send video and commentary of live operations from Sweden and San Francisco to a workshop held in London. These sessions were marred by severe congestion experienced on the networks on the day, but the consensus of those organising and attending the workshop was that the exercise was worthwhile. The main lessons learnt from this first transmission were the need to provide better quality links and to ensure confidentiality. In December 1995, the MERCI project, funded by the European Union under the TELEMATICS for Research programme, began work to refine and further propagate the use of the multimedia conferencing software. Part of this work is to provide these improved facilities to transmit operations to two more workshops scheduled for 1997. MERCI will offer confidentiality through encryption facilities built into the conferencing programs, improved programs which cope better with adverse network conditions, use of the new high-speed JAMES network and access to a multimedia server from which recordings of operations and medical instrumentation can be delivered to the workshop participants.     

Further studies on a DTBX prototype for the CMS muon detector at LHC

The performance of a small prototype chamber of the baseline project for the muon barrel detector for CMS has been studied in a muon beam. Its efficiency with different gases and wire diameters, the trigger possibilities and the response in presence of a large number of electromagnetic secondaries associated to the muon are evaluated. The results are compared with a full Monte Carlo simulation.     

Voltammetric determination of methylmercury and inorganic mercury with an home made gold nanoparticle electrode

This study outlines the development of a procedure for the determination of methylmercury by anodic stripping voltammetry at a gold nanoparticle-modified glassy carbon electrode (AuNPs-GCE) and for the differentiation between methylmercury and inorganic mercury. The signal of methylmercury was measured in the square wave mode using HCl as the supporting electrolyte. The procedure had good accuracy, repeatability and linearity. The determination of total mercury in solutions containing both methylmercury and inorganic mercury was performed after converting the former into the inorganic form. Different sample solution pre-treatments were tested for this purpose, and an acid digestion in a microwave oven with HNO₃ and H₂O₂ was found to be the most effective. The selective determination of methylmercury in the presence of inorganic mercury was possible after masking the latter through reduction to the elemental state with SnCl₂. The amount of inorganic mercury was determined by difference.     

Sources and sinks of hydroxyl radicals upon irradiation of natural water samples

Hydroxyl radical formation rates, steady-state concentration, and overall scavenging rate constant were measured by irradiation of surface lake water samples from Piedmont (NW Italy) and nitrate-rich groundwater samples from Moldova (NE Romania). Dissolved organic matter (DOM) was the main source and sink of *OH upon lake water irradiation, with [*OH] being independent of DOM amount. Water oxidation by photoexcited DOM is a likely *OH source in the presence of very low levels of nitrate and dissolved iron. Under different circumstances it is not possible to exclude other processes, e.g., DOM-enhanced photo-Fenton reactions. Under the hypotheses of no interaction and absence of mutual screening of radiation, nitrate would prevail over DOM as *OH source for a NO3-/DOM ratio higher than 3.3 x 10(-5) (mol NO3-) (mg C)(-1), DOM prevailing for lower values. Substantial DOM photolability was observed upon irradiation of nitrate-rich groundwater, mainly due to the elevated *OH generation rate. For the first time to our knowledge, evidence was also obtained of the photoformation of potentially toxic and/or mutagenic nitroaromatic compounds upon irradiation of natural lake water and groundwater samples, proportionally to the nitrate levels.