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.

Micromechanics of dentin/adhesive interface in function of dentin depth: 3d finite element analysis

Objectives: The aim of this study was to analyze the stress distribution on dentin/adhesive interface (d/a) through a 3-D finite element analysis (FEA) varying the number and diameter of the dentin tubules orifice according to dentin depth, keeping hybrid layer (HL) thickness and TAǴs length constant. Materials and Methods: 3 models were built through the SolidWorks software: SD - specimen simulating superficial dentin (41 x 41 x 82 μm), with a 3 μm thick HL, a 17 μm length Tag, and 8 tubules with a 0.9 μm diameter restored with composite resin. MD - similar to M1 with 12 tubules with a 1.2 μm diameter, simulating medium dentin. DD - similar to M1 with 16 tubules with a 2.5 μm diameter, simulating deep dentin. Other two models were built in order to keep the diameter constant in 2.5 μm: MS - similar to SD with 8 tubules; and MM - similar to MD with 12 tubules. The boundary condition was applied to the base surface of each specimen. Tensile load (0.03N) was performed on the composite resin top surface. Stress field (maximum principal stress in tension - σMAX) was performed using Ansys Wokbench 10.0. Results: The peak of σMAX (MPa) were similar between SD (110) and MD (106), and higher for DD (134). The stress distribution pathway was similar for all models, starting from peritubular dentin to adhesive layer, intertubular dentin and hybrid layer. The peak of σMAX (MPa) for those structures was, respectively: 134 (DD), 56.9 (SD), 45.5 (DD), and 36.7 (MD). Conclusions: The number of dentin tubules had no influence in the σMAX at the dentin/adhesive interface. Peritubular and intertubular dentin showed higher stress with the bigger dentin tubules orifice condition. The σMAX in the hybrid layer and adhesive layer were going down from superficial dentin to deeper dentin. In a failure scenario, the hybrid layer in contact with peritubular dentin and adhesive layer is the first region for breaking the adhesion. © 2011 Nova Science Publishers, Inc.

3D semantic models for dental education

This paper explores the benefits of using immersive and interactive virtual reality environments to teach Dentistry. We present a tool for educators to manipulate and edit virtual models. One of the main contributions is that multimedia information can be semantically associated with parts of the model, through an ontology, enriching the experience; for example, videos can be linked to each tooth demonstrating how to extract them. The use of semantic information gives a greater flexibility to the models, since filters can be applied to create temporary models that show subsets of the original data in a human friendly way. We also explain how the software was written to run in arbitrary multi-projection environments. © 2011 Springer-Verlag.

Automatic segmentation of the secondary austenite-phase island precipitates in a superduplex stainless steel weld metal

Duplex and superduplex stainless steels are class of materials of a high importance for engineering purposes, since they have good mechanical properties combination and also are very resistant to corrosion. It is known as well that the chemical composition of such steels is very important to maintain some desired properties. In the past years, some works have reported that γ 2 precipitation improves the toughness of such steels, and its quantification may reveals some important information about steel quality. Thus, we propose in this work the automatic segmentation of γ 2 precipitation using two pattern recognition techniques: Optimum-Path Forest (OPF) and a Bayesian classifier. To the best of our knowledge, this if the first time that machine learning techniques are applied into this area. The experimental results showed that both techniques achieved similar and good recognition rates. © 2012 Taylor & Francis Group.

Semiautomatic dental recognition using a graph-based segmentation algorithm and teeth shapes features

Dental recognition is very important for forensic human identification, mainly regarding the mass disasters, which have frequently happened due to tsunamis, airplanes crashes, etc. Algorithms for automatic, precise, and robust teeth segmentation from radiograph images are crucial for dental recognition. In this work we propose the use of a graph-based algorithm to extract the teeth contours from panoramic dental radiographs that are used as dental features. In order to assess our proposal, we have carried out experiments using a database of 1126 tooth images, obtained from 40 panoramic dental radiograph images from 20 individuals. The results of the graph-based algorithm was qualitatively assessed by a human expert who reported excellent scores. For dental recognition we propose the use of the teeth shapes as biometric features, by the means of BAS (Bean Angle Statistics) and Shape Context descriptors. The BAS descriptors showed, on the same database, a better performance (EER 14%) than the Shape Context (EER 20%). © 2012 IEEE.

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.

Heterogeneous demand and market segmentation: the Argentine pension funds system

Includes bibliography

Existence of solutions for the 3D-micropolar fluid system with initial data in Besov-Morrey spaces

In this paper, we show a local-in-time existence result for the 3D micropolar fluid system in the framework of Besov-Morrey spaces. The initial data class is larger than the previous ones and contains strongly singular functions and measures. © 2013 Springer Basel.

Platelet lysate 3D scaffold supports mesenchymal stem cell chondrogenesis: An improved approach in cartilage tissue engineering

Articular lesions are still a major challenge in orthopedics because of cartilage's poor healing properties. A major improvement in therapeutics was the development of autologous chondrocytes implantation (ACI), a biotechnology-derived technique that delivers healthy autologous chondrocytes after in vitro expansion. To obtain cartilage-like tissue, 3D scaffolds are essential to maintain chondrocyte differentiated status. Currently, bioactive 3D scaffolds are promising as they can deliver growth factors, cytokines, and hormones to the cells, giving them a boost to attach, proliferate, induce protein synthesis, and differentiate. Using mesenchymal stem cells (MSCs) differentiated into chondrocytes, one can avoid cartilage harvesting. Thus, we investigated the potential use of a platelet-lysate-based 3D bioactive scaffold to support chondrogenic differentiation and maintenance of MSCs. The MSCs from adult rabbit bone marrow (n=5) were cultivated and characterized using three antibodies by flow cytometry. MSCs (1×105) were than encapsulated inside 60μl of a rabbit platelet-lysate clot scaffold and maintained in Dulbecco's Modified Eagle Medium Nutrient Mixture F-12 supplemented with chondrogenic inductors. After 21 days, the MSCs-seeded scaffolds were processed for histological analysis and stained with toluidine blue. This scaffold was able to maintain round-shaped cells, typical chondrocyte metachromatic extracellular matrix deposition, and isogenous group formation. Cells accumulated inside lacunae and cytoplasm lipid droplets were other observed typical chondrocyte features. In conclusion, the usage of a platelet-lysate bioactive scaffold, associated with a suitable chondrogenic culture medium, supports MSCs chondrogenesis. As such, it offers an alternative tool for cartilage engineering research and ACI. © 2013 Informa UK Ltd.

Bone apposition to laminin-1 coated implants: Histologic and 3D evaluation

Laminin-1 has been reported as one of the factors responsible for the nucleation of calcium phosphates and, in vitro, has been reported to selectively recruit osteoprogenitors. This article focused on its in vivo effects, and evaluated the effect of laminin-1 local application on osseointegration. Polished cylindrical hydroxyapatite implants were coated with laminin-1 (test) and the bone responses in the rabbit tibiae after 2 and 4 weeks were evaluated and compared to the non-coated implants (control). Before the samples were processed for histological sectioning, they were three-dimensionally analysed with micro computed tomography (μCT). Both evaluation methods were analysed with regards to bone area around the implant and bone to implant contact. From the histologic observation, new bone formation around the laminin-1 coated implant at 2 weeks seemed to have increased the amount of supporting bone around the implant, however, at 4 weeks, the two groups presented no notable differences. The two-dimensional and three-dimensional morphometric evaluation revealed that both histologic and three-dimensional analysis showed some tendency in favour of the test group implants, however there was no statistical significance between the test and control group results. © 2012 International Association of Oral and Maxillofacial Surgeons.

Free tools and strategies for the generation of 3D finite element meshes: Modeling of the cardiac structures

The Finite Element Method is a well-known technique, being extensively applied in different areas. Studies using the Finite Element Method (FEM) are targeted to improve cardiac ablation procedures. For such simulations, the finite element meshes should consider the size and histological features of the target structures. However, it is possible to verify that some methods or tools used to generate meshes of human body structures are still limited, due to nondetailed models, nontrivial preprocessing, or mainly limitation in the use condition. In this paper, alternatives are demonstrated to solid modeling and automatic generation of highly refined tetrahedral meshes, with quality compatible with other studies focused on mesh generation. The innovations presented here are strategies to integrate Open Source Software (OSS). The chosen techniques and strategies are presented and discussed, considering cardiac structures as a first application context. © 2013 E. Pavarino et al.

Tilted and Short Implants Supporting Fixed Prosthesis in an Atrophic Maxilla: A 3D-FEA Biomechanical Evaluation

Purpose: This study compared the biomechanical behavior of tilted long implant and vertical short implants to support fixed prosthesis in an atrophic maxilla. Materials and Methods: The maxilla model was built based on a tomographic image of the patient. Implant models were based on micro-computer tomography imaging of implants. The different configurations considered were M4S, four vertical anterior implants; M4T, two mesial vertical implants and two distal tilted (45°) implants in the anterior region of the maxilla; and M6S, four vertical anterior implants and two vertical posterior implants. Numerical simulation was carried out under bilateral 150N loads applied in the cantilever region in axial (L1) and oblique (45°) (L2) direction. Bone was analyzed using the maximum and minimum principal stress (σmax and σmin), and von Mises stress (σvM) assessments. Implants were analyzed using the σvM. Results: The higher σmax was observed at: M4T, followed by M6S/L1, M6S/L2, M4S/L2, and M4S/L1 and the higher σvM: M4T/L1, M4T/L2 and M4S/L2, M6S/L2, M4S/L1, and M6S/L1. Conclusions: The presence of distal tilted (all-on-four) and distal short implants (all-on-six) resulted in higher stresses in both situations in the maxillary bone in comparison to the presence of vertical implants (all-on-four). © 2013 Wiley Periodicals, Inc.