Looking for an accurate and cost-effective solution to measure feed inventories, forecast the feed demand and allow feed suppliers to optimize inventories, production batches, and delivery routes.

Although low cost red-green-blue-depth (RGB-D) cameras are factory calibrated, to meet the accuracy requirements needed in many industrial applications proper calibration strategies have to be applied. Generally, these strategies do not consider the effect of temperature on the camera measurements. The aim of this paper is to evaluate this effect considering an Orbbec Astra camera. To analyze this camera performance, an experimental study in a thermal chamber has been carried out. From this experiment, it has been seen that produced errors can be modeled as an hyperbolic paraboloid function. To compensate for this error, a two-step method that first computes the error and then corrects it has been proposed. To compute the error two possible strategies are proposed, one based on the infrared distortion map and the other on the depth map. The proposed method has been tested in an experimental scenario with different Orbbec Astra cameras and also in a real environment. In both cases, its good performance has been demonstrated. In addition, the method has been compared with the Kinect v1 achieving similar results. Therefore, the proposed method corrects the error due to temperature, is simple, requires a low computational cost and might be applicable to other similar cameras.

In the context of a supply chain for the animal-feed industry, this paper focuses on optimizing replenishment strategies for silos in multiple farms. Assuming that a supply chain is essentially a value chain, our work aims at narrowing this chasm and putting analytics into practice by identifying and quantifying improvements on specific stages of an animal-feed supply chain. Motivated by a real-life case, the paper analyses a rich multi-period inventory routing problem with homogeneous fleet, stochastic demands, and maximum route length. After describing the problem and reviewing the related literature, we introduce a reactive heuristic, which is then extended into a biased-randomized simheuristic. Our reactive approach is validated and tested using a series of adapted instances to explore the gap between the solutions it provides and the ones generated by existing nonreactive approaches.

The animal feed supply chain to farm, mainly represented by the feed suppliers and livestock farmers, currently faces great inefficiencies due to outdated supply chain management.Stakeholders struggle with the timing and quantity evaluation when restocking their feed bins, significantly affecting cost and labour efficiency.However, the lack of accurate and cost-effective sensors to measure stock levels of solid materials stored in containers and open piles is preventing the implementation of these strategies in a large number of industrial sectors.In these cases, traditional technologies cannot offer a convenient solution due to an inevitable trade-off between accuracy and cost.This work develops an integral feedstock management system to optimise the entire supply chain.A new monitoring system based on an RGB-D sensor is presented as well as the data processing pipeline from raw depth measurements to bin specific daily consumption rates.

This paper discusses how the Internet of Things and simulation-based optimization methods can be effectively combined to enhance refilling strategies in an animal feed supply chain. Motivated by a real-life case study, the paper analyses a multi-period inventory routing problem with stochastic demands. After describing the problem and reviewing the related literature, a simulation-based optimization approach is introduced and tested via a series of computational experiments. Our approach combines biased-randomization techniques with a simheuristic framework to make use of data provided by smart sensor devices located at the top of each farm silo. From the analysis of results, some managerial insights are also derived and a new business model is proposed.

Multivariate imaging technologies such as Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) have recently gained an important attention as it improves tumour detection. Modelling of contrast media uptake and washout kinetic parameters which are closely related to physiological and anatomical features helps to diagnose and detect a possible cancer. One issue that does not generally receive much attention is the process of detecting regions of interest (ROIs). An automatic region-of-interest (ROI) selection method is presented to avoid the time consuming and subjective task of manual ROI selection, which significantly affects reproducibility and accuracy of measurements.

This paper presents a novel methodology to obtain the breast skin line in mammographic images. The breast edge provides important information of the breast shape and deformation which is posteriorly used by other processing techniques, typically mammographic image registration and abnormality detection. The proposed methodology is based on applying edge detection algorithms and scale space concepts. The proposed method is a particular implementation (application focused) of a growing active contour with common considerations. Quantitative and qualitative evaluation is provided to show the validity of the approach.

The detection of architectural distortions and abnormal structures in mammographic images can be based on the analysis of bilateral and temporal cases. This paper presents a novel method for mammographic image registration inspired by existing robust point matching approaches. This novel method is compared with other registration approaches proposed in the literature using both quantitative and qualitative evaluation based on similarity metrics and ROC analysis (ground truth provided by an expert radiologist). Initial evaluation is based on mammographic data of 64 women with malignant masses which indicates the accuracy and robustness of our method.

Advances in the area of computerized image analysis applied to mammography may have very important practical applications in automatically detecting asymmetries (masses, architectural distortions, etc.) between the two breasts. We have developed a fully automatic technique to detect the breast border and the nipple, this being a necessary prerequisite for further image analysis. To detect the breast border, an algorithm that computes the gradient of gray levels was applied. To detect the nipple, three algorithms were compared (maximum height of the breast border, maximum gradient, and maximum second derivative of the gray levels across the median-top section of the breast). A combined method was also designed. The algorithms were tested on 156 digitized mammograms. The breast segmentation results were evaluated by two expert radiologists and one physicist. In 89% of the mammograms, the computed border was in close agreement with the radiologist's estimated border. Segmentation results were acceptable to be used in computer-aided diagnostic schemes. The mean distance between the position of the nipple indicated by two radiologists by consensus and the position calculated by the computer was 6 mm.

Previous works on breast tissue identification and abnormalities detection notice that the feature extraction process is affected if the region processed is not well focused. Thereby, it is important to split the mammogram into interesting regions to achieve optimal breast parenchyma measurements, breast registration or to put into focus a technique when we search for abnormalities. In this paper, we review most of the relevant work that has been presented from 80's to nowadays. Secondly, an automated technique for segmenting a digital mammogram into breast region and background, with pectoral muscle suppression is presented.

Peroxidases have broad applications in industry, environmental as well as pharmaceutical and diagnosis. Recently applicability of peroxidases in cancer therapy was mentioned. In the present study, a horseradish peroxidase homologue from Lepidium draba was subjected to in silico analyzes aiming at identifying and locating immune-reactive regions. A derivative sequence with decreased immunogenicity and increased stability also suggested. The tertiary structure of the enzyme was predicted. The functional and structural importance of residues was annotated as well as the conservatory status of each residue. The immune-dominant regions of protein were predicted with various software. N-terminal 4 residues, NFSHTGL (186–192), PRNGN (210–214), PLVRAYADGTQKFFN (261–275), and last 4 residues in C-terminal were predicted to be the consensus immunogenic segments of L. draba peroxidase. The modifications were applied to wild type sequence in order to mitigate its immune-reactiveness. The modifications were based on predicted energetic status of residues and naturally occurred amino acids in each position of the enzyme sequence, extracted from alignment file of 150 homologous peroxidases. The new enzyme derivative is predicted to be less immune-reactive and more stable. Thus the sequence is better suited to therapeutic applications.

One of the applications of image registration is to assess object differences from various images that have been spatially correlated. This paper discusses the use of features extracted from subtracted registered images in a classification framework with an aim to detect abnormal mammograms. Both quantitative and qualitative results are provided, which show that although non-optimal classification is obtained, region features extracted after registration can be used to discriminate between normal and abnormal mammograms.

A recent trend in digital mammography are CAD systems, which are computerized tools designed to help radiologists. Most of these systems are used for the automatic detection of abnormalities. However, recent studies have shown that their sensitivity is significantly decreased as the density of the breast is increased. In addition, the suitability of abnormality segmentation approaches tends to depend on breast tissue density. In this paper we propose a new approach to the classification of mammographic images according to the breast parenchymal density. Our classification is based on gross segmentation and the underlying texture contained within the breast tissue. Robustness and classification performance are evaluated on a set of digitized mammograms, applying different classifiers and leave-one-out for training. Results demonstrate the feasibility of estimating breast density using computer vision techniques.

We have investigated a combination of statistical modelling and expectation maximisation for a texture based approach to the segmentation of mammographic images. Texture modelling is based on the implicit incorporation of spatial information through the introduction of a set-permutation-occurrence matrix. Statistical modelling is used for data generalisation and noise removal purposes. Expectation maximisation modelling of the spatial information in combination with the statistical modelling is evaluated. The developed segmentation results are used for automatic mammographic risk assessment.

We have investigated a combination of statistical modelling and expectation maximisation for a texture based approach to the segmentation of mammographic images. Texture modelling is based on the implicit incorporation of spatial information through the introduction of a set-permutation-occurrence matrix. Statistical modelling is used for dimensionality reduction, data generalisation and noise removal purposes. Expectation maximisation modelling of the resulting feature vector provides the basis for image segmentation. The developed segmentation results are used for automatic mammographic risk assessment.

Image segmentation has been, and still is, a relevant research area in Computer Vision, and hundreds of segmentation algorithms have been proposed in the last 30 years. However, it is well known that elemental segmentation techniques based on boundary or region information often fail to produce accurate segmentation results. Hence, in the last few years, there has been a tendency towards algorithms which take advantage of the complementary nature of such information. This paper reviews different segmentation proposals which integrate edge and region information and highlights 7 different strategies and methods to fuse such information. In contrast with other surveys which only describe and compare qualitatively different approaches, this survey deals with a real quantitative comparison. In this sense, key methods have been programmed and their accuracy analyzed and compared using synthetic and real images. A discussion justified with experimental results is given and the code is available on Internet.

Resumen: En este trabajo presentamos HRIMAC, un proyecto concebido para funcionar como un sistema de recuperación de imágenes por contenido que permita acceder a una determinada tipología de imágenes de mamografías digitales almacenadas en las di- versas bases de datos públicas, a partir del contenido de una imagen ejemplo, si- guiendo determinados criterios de afinidad. Así, a partir de una imagen mamográfica sobre la cual se pretende emitir un diagnóstico, HRIMAC busca en la base de datos mamográfica las n mamografías más similares, de acuerdo con los criterios especifi- cados en la búsqueda. De esta manera, cada búsqueda proporciona un conjunto limitado de casos (mamografías digitales) con ciertas características (la forma de los clusters de microcalcificaciones, la presencia de determinadas lesiones espiculares, la forma de las masas, etc.) muy similares a la mamografía que se somete a estudio. El análisis de estos casos, ya patológicos, puede sin lugar a dudas ayudar al radiólogo a diagnosticar con más garantías de éxito, y aumentar de esta forma el grado de efica- cia en la interpretación.