Avaliação do método de classificação baseada no objeto em imagens de alta resolução espacial aplicado para o monitoramento de faixa de dutos: estudo de caso no entorno da refinaria de Capuava em Mauá - SP

The metropolitan region of São Paulo is the most populous of the country, this happens because of its great importance in the national economy and the job opportunities that are offered to the population. These factors result in intense population growth and urban expansion, reaching some non-habitable places of the metropolis, as areas of pipelines, which are very important for the transportation of natural gas, oil and its derivatives. Before the population growth of the region, these sites were unoccupied, do not presenting problems for the population. However, with the disorderly occupation is generated great anthropogenic pressure on the pipeline stitches, causing risks to people who are around them. Therefore it is extremely important to monitor the strip of pipelines through products and techniques of remote sensing and geoprocessing, enabling, through high spatial resolution images, identification of objects or phenomena that occur on Earth's surface that can alter the functioning and safety of pipelines. Therefore, this study aims to monitor a stretch of the area of the pipeline mesh GASPAL/OSVAT and Capuava Refinery (RECAP), located on the outskirts of the metropolitan area of São Paulo in the city of Mauá, who suffer great human pressure, proving thus the techniques of remote sensing and geographic information system (GIS) as effective tools for monitoring phenomena occurred in urban areas of great complexity. The monitoring was done by object-based classification applied in orbital images Ikonos II and RapidEye, of high spatial resolution and, image processing, detection of objects, segmentation, classification and editing were developed through the eCognition and ArcGis softwares. To determine the statistical accuracy of the mapping of the land cover of the stretch of pipeline in Maua, the results were analyzed by error matrix... (Complete abstract click electronic access below)

IFTrace: Video segmentation of deformable objects using the Image Foresting Transform

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Automatic segmentation of latent fingerprints

Latent fingerprints are routinely found at crime scenes due to the inadvertent contact of the criminals' finger tips with various objects. As such, they have been used as crucial evidence for identifying and convicting criminals by law enforcement agencies. However, compared to plain and rolled prints, latent fingerprints usually have poor quality of ridge impressions with small fingerprint area, and contain large overlap between the foreground area (friction ridge pattern) and structured or random noise in the background. Accordingly, latent fingerprint segmentation is a difficult problem. In this paper, we propose a latent fingerprint segmentation algorithm whose goal is to separate the fingerprint region (region of interest) from background. Our algorithm utilizes both ridge orientation and frequency features. The orientation tensor is used to obtain the symmetric patterns of fingerprint ridge orientation, and local Fourier analysis method is used to estimate the local ridge frequency of the latent fingerprint. Candidate fingerprint (foreground) regions are obtained for each feature type; an intersection of regions from orientation and frequency features localizes the true latent fingerprint regions. To verify the viability of the proposed segmentation algorithm, we evaluated the segmentation results in two aspects: a comparison with the ground truth foreground and matching performance based on segmented region. © 2012 IEEE.

Extração automática de contornos de telhados usando dados de varredura a laser e campos randômicos de Markov

This paper proposes a methodology for automatic extraction of building roof contours from a Digital Elevation Model (DEM), which is generated through the regularization of an available laser point cloud. The methodology is based on two steps. First, in order to detect high objects (buildings, trees etc.), the DEM is segmented through a recursive splitting technique and a Bayesian merging technique. The recursive splitting technique uses the quadtree structure for subdividing the DEM into homogeneous regions. In order to minimize the fragmentation, which is commonly observed in the results of the recursive splitting segmentation, a region merging technique based on the Bayesian framework is applied to the previously segmented data. The high object polygons are extracted by using vectorization and polygonization techniques. Second, the building roof contours are identified among all high objects extracted previously. Taking into account some roof properties and some feature measurements (e. g., area, rectangularity, and angles between principal axes of the roofs), an energy function was developed based on the Markov Random Field (MRF) model. The solution of this function is a polygon set corresponding to building roof contours and is found by using a minimization technique, like the Simulated Annealing (SA) algorithm. Experiments carried out with laser scanning DEM's showed that the methodology works properly, as it delivered roof contours with approximately 90% shape accuracy and no false positive was verified.

Recursive hierarchic segmentation analysis of bone mineral density changes on digital panoramic images

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Effects of meal size and proximal-distal segmentation on gastric activity

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Anatomicosurgical arterial segmentation of the cat lungs (Felis catus domesticus, L., 1758)

O objetivo desta pesquisa foi estabelecer os segmentos anátomo-cirúrgicos arteriais, através da lobação e ramificação intralobar arterial, em pulmões de gato. Após a dissecção de vinte pulmões, notou-se que a artéria pulmonar direita geralmente emite um ramo para o lobo cranial e um ramo para o lobo médio, sendo originados juntos em um tronco. Um grande ramo irriga o lobo caudal na maioria dos casos. Dois ramos com origem comum no ramo arterial do lobo caudal irrigam o lobo acessório. A artéria pulmonar esquerda origina um tronco que, na maioria dos casos, emite um ramo para a porção cranial e um ramo para a porção caudal do lobo cranial esquerdo. Pode-se concluir que o pulmão direito é formado por quatro e o esquerdo por dois lobos, ocorrendo variações na ramificação arterial pulmonar.

Denisiuk-type reflection holography display with sillenite crystals for imaging and interferometry of small objects

A novel setup for imaging and interferometry through reflection holography with Bi12TiPO20(BTO) sillenite photorefractive crystals is proposed. A variation of the lensless Denisiuk arrangement was developed resulting in a compact, robust and simple interferometer. A red He-Ne laser was used as light source and the holographic recording occurred by diffusion with the grating vector parallel to the crystal [0 0 1]-axis. In order to enhance the holographic image quality and reduce noise a polarizing beam splitter (PBS) was positioned at the BTO input and the crystal was tilted around the [0 0 1]-axis. This enabled the orthogonally polarized transmission and diffracted beams to be separated by the PBS, providing the holographic image only. The possibility of performing deformation and strain analysis as well as vibration measurement of small objects was demonstrated. (C) 2007 Elsevier B.V. All rights reserved.

A method for the digital image analysis of ceramic grains based on shape factor segmentation

A very simple and robust method for ceramics grains quantitative image analysis is presented. Based on the use of optimal imaging conditions for reflective light microscopy of bulk samples, a digital image processing routine was developed for shading correction, noise suppressing and contours enhancement. Image analysis was done for grains selected according to their concavities, evaluated by perimeter ratio shape factor, to avoid consider the effects of breakouts and ghost boundaries due to ceramographic preparation limitations. As an example, the method was applied for two ceramics, to compare grain size and morphology distributions. In this case, most of artefacts introduced by ceramographic preparation could be discarded due to the use of perimeter ratio exclusion range.

Segmentação de dados de perfilamento a laser em áreas urbanas utilizando uma abordagem Bayesiana

In this paper is presented a region-based methodology for Digital Elevation Model segmentation obtained from laser scanning data. The methodology is based on two sequential techniques, i.e., a recursive splitting technique using the quad tree structure followed by a region merging technique using the Markov Random Field model. The recursive splitting technique starts splitting the Digital Elevation Model into homogeneous regions. However, due to slight height differences in the Digital Elevation Model, region fragmentation can be relatively high. In order to minimize the fragmentation, a region merging technique based on the Markov Random Field model is applied to the previously segmented data. The resulting regions are firstly structured by using the so-called Region Adjacency Graph. Each node of the Region Adjacency Graph represents a region of the Digital Elevation Model segmented and two nodes have connectivity between them if corresponding regions share a common boundary. Next it is assumed that the random variable related to each node, follows the Markov Random Field model. This hypothesis allows the derivation of the posteriori probability distribution function whose solution is obtained by the Maximum a Posteriori estimation. Regions presenting high probability of similarity are merged. Experiments carried out with laser scanning data showed that the methodology allows to separate the objects in the Digital Elevation Model with a low amount of fragmentation.

JSEG-based image segmentation in computer vision for agricultural mobile robot navigation

This project aims to apply image processing techniques in computer vision featuring an omnidirectional vision system to agricultural mobile robots (AMR) used for trajectory navigation problems, as well as localization matters. To carry through this task, computational methods based on the JSEG algorithm were used to provide the classification and the characterization of such problems, together with Artificial Neural Networks (ANN) for pattern recognition. Therefore, it was possible to run simulations and carry out analyses of the performance of JSEG image segmentation technique through Matlab/Octave platforms, along with the application of customized Back-propagation algorithm and statistical methods in a Simulink environment. Having the aforementioned procedures been done, it was practicable to classify and also characterize the HSV space color segments, not to mention allow the recognition of patterns in which reasonably accurate results were obtained.

Fast automatic microstructural segmentation of ferrous alloy samples using optimum-path forest

In this work we propose a novel automatic cast iron segmentation approach based on the Optimum-Path Forest classifier (OPF). Microscopic images from nodular, gray and malleable cast irons are segmented using OPF, and Support Vector Machines (SVM) with Radial Basis Function and SVM without kernel mapping. Results show accurate and fast segmented images, in which OPF outperformed SVMs. Our work is the first into applying OPF for automatic cast iron segmentation. © 2010 Springer-Verlag.

Automatic segmentation of digital images applied in cardiac medical images

The digital image processing has been applied in several areas, especially where it is necessary use tools for feature extraction and to get patterns of the studied images. In an initial stage, the segmentation is used to separate the image in parts that represents a interest object, that may be used in a specific study. There are several methods that intends to perform such task, but is difficult to find a method that can easily adapt to different type of images, that often are very complex or specific. To resolve this problem, this project aims to presents a adaptable segmentation method, that can be applied to different type of images, providing an better segmentation. The proposed method is based in a model of automatic multilevel thresholding and considers techniques of group histogram quantization, analysis of the histogram slope percentage and calculation of maximum entropy to define the threshold. The technique was applied to segment the cell core and potential rejection of tissue in myocardial images of biopsies from cardiac transplant. The results are significant in comparison with those provided by one of the best known segmentation methods available in the literature. © 2010 IEEE.

Precipitates segmentation from scanning electron microscope images through machine learning techniques

The presence of precipitates in metallic materials affects its durability, resistance and mechanical properties. Hence, its automatic identification by image processing and machine learning techniques may lead to reliable and efficient assessments on the materials. In this paper, we introduce four widely used supervised pattern recognition techniques to accomplish metallic precipitates segmentation in scanning electron microscope images from dissimilar welding on a Hastelloy C-276 alloy: Support Vector Machines, Optimum-Path Forest, Self Organizing Maps and a Bayesian classifier. Experimental results demonstrated that all classifiers achieved similar recognition rates with good results validated by an expert in metallographic image analysis. © 2011 Springer-Verlag Berlin Heidelberg.

Extração de vias combinando métodos de detecção de regiões e linhas em imagens de intensidade de pulso laser

This paper aims at extracting street centerlines from previously isolated street regions by using the image of laser scanning intensity. In this image, streets are easily identified, since they manifest as dark, elongate ribbons contrasting with background objects. The intensity image is segmented by using the region growing technique, which generates regions representing the streets. From these regions, the street centerlines are extracted in two manners. The first one is through the Steger lines detection method combined with a line length thresholding by which lines being shorter than a minimum length are removed. The other manner is by combining the skeletonization method of regions based on the Medial Axis Transform and with a pruning process to eliminate as much as possible the ramifications. Experiments showed that the Steger-based method provided results better than the method based on skeletonization.