A mechatronic system applied to wear particle analysis

This paper describes the development of a mechatronic system for a predictive maintenance grounded on wear particle analysis. The reckoning of wear particles containing in lubricating industrial oils brings the image acquisition system into being. The ISO 4406:1999 standard is a guide to establish the counting and evaluation processes of particles. The system applied to the acquisition and analysis of the data consists of a digital camera, a monocular microscope and an oil filtering system. A computational program was developed with the application of Visual Microsoft C++ in a way to detain the oil sample image from the microscope slide to the computer screen. Quantitative analyses of the wear debris particles bulk are exploited applying a graphical interface that was developed to render the image processing of the sample test. The implemented system has a reachable cost thus it can be applied for schooling goals and for bolstering laboratories of minor industries and medium size companies.

Geoprocessamento e sensoriamento remoto aplicado na determinação da aptidão agrícola de uma microbacia

Soil use for the development of activities as agriculture and livestock has been causing great alterations in the environment, mainly when these are practiced intensively, disrespecting the fragility and aptitude of the natural resources. Therefore, it is essential that the planning of the agricultural activities is done, taking into consideration the several environmental criteria involved in the decision-making process. Thus, this study aimed to analyze the agricultural aptitude classes of lands from a watershed through geographical information system (GIS). The Arroio Ajuricaba watershed is located in the Municipality of Marechal Cândido Rondon - PR among the coordinates UTM 787309m E and 793892m E; 7275026m N and 7281310m N, in the Spindle 21, presenting an area of 1681ha. Soil maps, in semi detail scale, was the digital cartographic base used. The results allowed to conclude that 42.41% of the basin presented a good aptitude for farming in handling level of high technology (handling level C), regular aptitude for B, and restricted aptitude for A [class 1(a)bC] and that 12% of the area had regular aptitude for farming in the three handling levels (class 1abc). The watershed lands (14.24%) presented regular aptitude for farming in handling level C, restricted aptitude for B, and inapt for A [class of aptitude 2(b)c]; 15.85% presented good aptitude for planted pasture (class 4P) and 12.21% were considered without aptitude for agricultural use (class 6). We can say that 71.94% of the lands has aptitude for farming, although they present different degrees of limitations that request different treatments for its conservation.

A regularized nonlinear diffusion approach for texture image denoising

In this paper a new partial differential equation based method is presented with a view to denoising images having textures. The proposed model combines a nonlinear anisotropic diffusion filter with recent harmonic analysis techniques. A wave atom shrinkage allied to detection by gradient technique is used to guide the diffusion process so as to smooth and maintain essential image characteristics. Two forcing terms are used to maintain and improve edges, boundaries and oscillatory features of an image having irregular details and texture. Experimental results show the performance of our model for texture preserving denoising when compared to recent methods in literature. © 2009 IEEE.

Assessment of manipulation accuracy of digitized occlusal radiographic images--sub and over exposure.

The aim of this study was to evaluate whether digitized images obtained from occlusal radiographs taken with low or over dose of radiation could be improved with the aid of computer software for digital treatment. Thirteen occlusal radiographs of a dry skull were taken employing 13 different exposure times. The radiographs were digitized and then manipulated with the program for image editing. 143 evaluations were performed by specialists in dental radiology who classified radiographs as appropriate or not appropriate for interpretation. Test Z was used for statistical analysis of the data and the results showed that it is possible to manipulate digitized radiographic images taken with 75% of the ideal exposure time and to make them suitable for interpretation and diagnosis. Conversely, it was concluded that the over exposed images, 57.50% above the standard exposure time, were inadequate.

ANN statistical image recognition method for computer vision in agricultural mobile robot navigation

The main application area in this project, is to deploy image processing and segmentation techniques in computer vision through an omnidirectional vision system to agricultural mobile robots (AMR) used for trajectory navigation problems, as well as localization matters. Thereby, 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 image recognition. Hence, it was possible to run simulations and carry out analyses of the performance of JSEG image segmentation technique through Matlab/Octave computational platforms, along with the application of customized Back-propagation Multilayer Perceptron (MLP) algorithm and statistical methods as structured heuristics 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 segmented images in which reasonably accurate results were obtained. © 2010 IEEE.

Geometric modeling from the medical images in the CAD system to support prosthesis design

This paper presents an individual designing prosthesis for surgical use and proposes a methodology for such design through mathematical extrapolation of data from digital images obtained via tomography of individual patient's bones. Individually tailored prosthesis designed to fit particular patient requirements as accurately as possible should result in more successful reconstruction, enable better planning before surgery and consequently fewer complications during surgery. Fast and accurate design and manufacture of personalized prosthesis for surgical use in bone replacement or reconstruction is potentially feasible through the application and integration of several different existing technologies, which are each at different stages of maturity. Initial case study experiments have been undertaken to validate the research concepts by making dimensional comparisons between a bone and a virtual model produced using the proposed methodology and a future research directions are discussed.

Image categorization through optimum path forest and visual words

Different from the first attempts to solve the image categorization problem (often based on global features), recently, several researchers have been tackling this research branch through a new vantage point - using features around locally invariant interest points and visual dictionaries. Although several advances have been done in the visual dictionaries literature in the past few years, a problem we still need to cope with is calculation of the number of representative words in the dictionary. Therefore, in this paper we introduce a new solution for automatically finding the number of visual words in an N-Way image categorization problem by means of supervised pattern classification based on optimum-path forest. © 2011 IEEE.

Identification of foliar diseases in cotton crop

The pathogens manifestation in plantations are the largest cause of damage in several cultivars, which may cause increase of prices and loss of crop quality. This paper presents a method for automatic classification of cotton diseases through feature extraction of leaf symptoms from digital images. Wavelet transform energy has been used for feature extraction while Support Vector Machine has been used for classification. Five situations have been diagnosed, namely: Healthy crop, Ramularia disease, Bacterial Blight, Ascochyta Blight, and unspecified disease. © 2012 Taylor & Francis Group.

Assessment of eyebrow position before and after upper eyelid blepharoplasty

Objective: Assess the occurrence of secondary brow ptosis after upper lid blepharoplasty. Methods: Forty-five individuals (n90 brows) submitted to upper lid blepharoplasty, were assessed by means of a comparative analysis using pre- and post-operatively digital photographs, in the primary position of the eye. The images were processed using ImageJ software, transferred to a computer, to an electronic Microsoft Excel 2002® worksheet. Angular measurements were used, taking the lateral canthal angle of the brow, the most medial point of the brow, the medial canthal angle and the lateral canthal angle of the lid as anatomical reference points. When the outer angles were reduced or the inner angles increased after surgery this was considered a brow ptosis. Individuals who had undergone lid surgery associated with the eyebrow, previous eyebrow surgery and those with eyelid ptosis were excluded. The difference between the pre-operative and post-operative measurements were analyzed statistically using the Student's t-test for paired samples and the angular variation was compared with their corresponding contralateral sample using Wilcoxon's non-parametric test. Results: The measurements obtained after the blepharoplasty show significant variations from those before the surgery, indicating that the correction of redundant tissues in the brow accentuates the tendency of the eyebrow to move down. The alterations are more important in the lateral portion of the eyebrow and they occur bilaterally. Conclusion: The assessment of angular measurements obtained pre- and post-operatively showed that there are secondary changes in the position of the eyebrow as a result of upper eyelid blepharoplasty. © 2012 Informa Healthcare USA, Inc.

A semi-automatic method for indirect orientation of aerial images using ground control lines extracted from airborne laser scanner data

This paper presents a method for indirect orientation of aerial images using ground control lines extracted from airborne Laser system (ALS) data. This data integration strategy has shown good potential in the automation of photogrammetric tasks, including the indirect orientation of images. The most important characteristic of the proposed approach is that the exterior orientation parameters (EOP) of a single or multiple images can be automatically computed with a space resection procedure from data derived from different sensors. The suggested method works as follows. Firstly, the straight lines are automatically extracted in the digital aerial image (s) and in the intensity image derived from an ALS data-set (S). Then, correspondence between s and S is automatically determined. A line-based coplanarity model that establishes the relationship between straight lines in the object and in the image space is used to estimate the EOP with the iterated extended Kalman filtering (IEKF). Implementation and testing of the method have employed data from different sensors. Experiments were conducted to assess the proposed method and the results obtained showed that the estimation of the EOP is function of ALS positional accuracy.

Improving image classification through descriptor combination

The efficiency in image classification tasks can be improved using combined information provided by several sources, such as shape, color, and texture visual properties. Although many works proposed to combine different feature vectors, we model the descriptor combination as an optimization problem to be addressed by evolutionary-based techniques, which compute distances between samples that maximize their separability in the feature space. The robustness of the proposed technique is assessed by the Optimum-Path Forest classifier. Experiments showed that the proposed methodology can outperform individual information provided by single descriptors in well-known public datasets. © 2012 IEEE.

Digital filtering of oscillations intrinsic to transmission line modeling based on lumped parameters

A correction procedure based on digital signal processing theory is proposed to smooth the numeric oscillations in electromagnetic transient simulation results from transmission line modeling based on an equivalent representation by lumped parameters. The proposed improvement to this well-known line representation is carried out with an Finite Impulse Response (FIR) digital filter used to exclude the high-frequency components associated with the spurious numeric oscillations. To prove the efficacy of this correction method, a well-established frequency-dependent line representation using state equations is modeled with an FIR filter included in the model. The results obtained from the state-space model with and without the FIR filtering are compared with the results simulated by a line model based on distributed parameters and inverse transforms. Finally, the line model integrated with the FIR filtering is also tested and validated based on simulations that include nonlinear and time-variable elements. © 2012 Elsevier Ltd. All rights reserved.

Geração automática de modelos digitais de superfícies utilizando múltiplas imagens

Pós-graduação em Ciências Cartográficas - FCT

Visualização 3D de uma imagem digital

Pós-graduação em Ciências Cartográficas - FCT

Imagem digital em movimento

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)