CENSUS HISTOGRAMS: A SIMPLE FEATURE EXTRACTION and MATCHING APPROACH FOR FACE RECOGNITION

Most face recognition approaches require a prior training where a given distribution of faces is assumed to further predict the identity of test faces. Such an approach may experience difficulty in identifying faces belonging to distributions different from the one provided during the training. A face recognition technique that performs well regardless of training is, therefore, interesting to consider as a basis of more sophisticated methods. In this work, the Census Transform is applied to describe the faces. Based on a scanning window which extracts local histograms of Census Features, we present a method that directly matches face samples. With this simple technique, 97.2% of the faces in the FERET fa/fb test were correctly recognized. Despite being an easy test set, we have found no other approaches in literature regarding straight comparisons of faces with such a performance. Also, a window for further improvement is presented. Among other techniques, we demonstrate how the use of SVMs over the Census Histogram representation can increase the recognition performance.

Uma nova forma de calcular os centros dos Clusters em algoritmos de agrupamento tipo fuzzy c-means

Clustering data is a very important task in data mining, image processing and pattern recognition problems. One of the most popular clustering algorithms is the Fuzzy C-Means (FCM). This thesis proposes to implement a new way of calculating the cluster centers in the procedure of FCM algorithm which are called ckMeans, and in some variants of FCM, in particular, here we apply it for those variants that use other distances. The goal of this change is to reduce the number of iterations and processing time of these algorithms without affecting the quality of the partition, or even to improve the number of correct classifications in some cases. Also, we developed an algorithm based on ckMeans to manipulate interval data considering interval membership degrees. This algorithm allows the representation of data without converting interval data into punctual ones, as it happens to other extensions of FCM that deal with interval data. In order to validate the proposed methodologies it was made a comparison between a clustering for ckMeans, K-Means and FCM algorithms (since the algorithm proposed in this paper to calculate the centers is similar to the K-Means) considering three different distances. We used several known databases. In this case, the results of Interval ckMeans were compared with the results of other clustering algorithms when applied to an interval database with minimum and maximum temperature of the month for a given year, referring to 37 cities distributed across continents

Novos métodos determinísticos para gerar centros iniciais dos grupos no algoritmo fuzzy C-Means e variantes

Data clustering is applied to various fields such as data mining, image processing and pattern recognition technique. Clustering algorithms splits a data set into clusters such that elements within the same cluster have a high degree of similarity, while elements belonging to different clusters have a high degree of dissimilarity. The Fuzzy C-Means Algorithm (FCM) is a fuzzy clustering algorithm most used and discussed in the literature. The performance of the FCM is strongly affected by the selection of the initial centers of the clusters. Therefore, the choice of a good set of initial cluster centers is very important for the performance of the algorithm. However, in FCM, the choice of initial centers is made randomly, making it difficult to find a good set. This paper proposes three new methods to obtain initial cluster centers, deterministically, the FCM algorithm, and can also be used in variants of the FCM. In this work these initialization methods were applied in variant ckMeans.With the proposed methods, we intend to obtain a set of initial centers which are close to the real cluster centers. With these new approaches startup if you want to reduce the number of iterations to converge these algorithms and processing time without affecting the quality of the cluster or even improve the quality in some cases. Accordingly, cluster validation indices were used to measure the quality of the clusters obtained by the modified FCM and ckMeans algorithms with the proposed initialization methods when applied to various data sets

Development of phantom for radiographic image optimization of standard patient in the lateral view of chest and skull examination

We present the construction of a homogeneous phantom to be used in simulating the scattering and absorption of X-rays by a standard patient chest and skull when irradiated laterally. This phantom consisted of Incite and aluminium plates with their thickness determined by a tomographic exploratory method applied to the anthropomorphic phantom. Using this phantom, an optimized radiographic technique was established for chest and skull of standard sized patient in lateral view. Images generated with this optimized technique demonstrated improved image quality and reduced radiation doses. (c) 2006 Elsevier Ltd. All rights reserved.

Aquisição, processamento e análise de dados de sísmica de alta resolução na plataforma continental norte do Rio Grande do Norte: Vale inciso do rio açu

On the modern Continental Shelf to the north of Rio Grande do Norte state (NE Brazil) is located a paleo-valley, submerged during the last glacial sea-level lowstand, that marks continuation of the most important river of this area (Açu River). Despite the high level of exploration activity of oil industry, there is few information about shallow stratigraphy. Aiming to fill this gap, situated on the Neogene, was worked a marine seismic investigation, the development of a processing flow for high resolution data seismic, and the recognition of the main feature morphology of the study area: the incised valley of the River Açu. The acquisition of shallow seismic data was undertaken in conjunction with the laboratory of Marine Geology/Geophysics and Environmental Monitoring - GGEMMA of Federal University of Rio Grande do Norte UFRN, in SISPLAT project, where the geomorphological structure of the Rio paleovale Açu was the target of the investigation survey. The acquisition of geophysical data has been over the longitudinal and transverse sections, which were subsequently submitted to the processing, hitherto little-used and / or few addressed in the literature, which provided a much higher quality result with the raw data. Once proposed for the flow data was developed and applied to the data of X-Star (acoustic sensor), using available resources of the program ReflexW 4.5 A surface fluvial architecture has been constructed from the bathymetric data and remote sensing image fused and draped over Digital Elevation Models to create three-dimensional (3D) perspective views that are used to analyze the 3D geometry geological features and provide the mapping morphologically defined. The results are expressed in the analysis of seismic sections that extend over the region of the continental shelf and upper slope from mouth of the Açu River to the shelf edge, providing the identification / quantification of geometrical features such as depth, thickness, horizons and units seismic stratigraphyc area, with emphasis has been placed on the palaeoenvironmental interpretation of discordance limit and fill sediment of the incised valley, control by structural elements, and marked by the influence of changes in the sea level. The interpretation of the evolution of this river is worth can bring information to enable more precise descriptions and interpretations, which describes the palaeoenvironmental controls influencing incised valley evolution and preservation to provide a better comprehensive understanding of this reservoir analog system

Feature selection through gravitational search algorithm

In this paper we deal with the problem of feature selection by introducing a new approach based on Gravitational Search Algorithm (GSA). The proposed algorithm combines the optimization behavior of GSA together with the speed of Optimum-Path Forest (OPF) classifier in order to provide a fast and accurate framework for feature selection. Experiments on datasets obtained from a wide range of applications, such as vowel recognition, image classification and fraud detection in power distribution systems are conducted in order to asses the robustness of the proposed technique against Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and a Particle Swarm Optimization (PSO)-based algorithm for feature selection.

Characterization and thermal behavior of residues from industrial sugarcane processing

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

An image analysis study of pit formation on Ti-6Al-4V

Metallographic techniques and digital image processing have been used to investigate heat-treated Ti-6Al-4V pitting corrosion, often used as aircraft components. LM and SEM metallography of 'as received', annealed (heating up to 800 degreesC/30 min and cooling furnace) and aged (heating up to 900 degreesC/30 min, quenching in water, heating up to 540 degreesC/240 min and again water-quenched) microstructures reveal pitting sites at primary and secondary alpha/beta interfaces. Microstructural arrangements influence and corrosive environment association on pit morphology could be demonstrated by digital image analysis and results statistical treatment. (C) 2002 Elsevier B.V. B.V. All rights reserved.

Automated extraction of road network from medium-and high-resolution images

This paper presents an automatic methodology for road network extraction from medium-and high-resolution aerial images. It is based on two steps. In the first step, the road seeds (i.e., road segments) are extracted using a set of four road objects and another set of connection rules among road objects. Each road object is a local representation of an approximately straight road fragment and its construction is based on a combination of polygons describing all relevant image edges, according to some rules embodying road knowledge. Each road seed is composed by a sequence of connected road objects in which each sequence of this type can be geometrically structured as a chain of contiguous quadrilaterals. In the second step, two strategies for road completion are applied in order to generate the complete road network. The first strategy is based on two basic perceptual grouping rules, i.e., proximity and collinearity rules, which allow the sequential reconstruction of gaps between every pair of disconnected road segments. This strategy does not allow the reconstruction of road crossings, but it allows the extraction of road centerlines from the contiguous quadrilaterals representing connected road segments. The second strategy for road completion aims at reconstructing road crossings. Firstly, the road centerlines are used to find reference points for road crossings, which are their approximate positions. Then these points are used to extract polygons representing the contours of road crossings. This paper presents the proposed methodology and experimental results. © Pleiades Publishing, Inc. 2006.

Comparison between inverted and unprocessed digitized radiographic imaging in periodontal bone loss measurements

The advances in digital imaging technology in dentistry have provided an alternative to film-based radiography and have given new options to detect periodontal bone loss. The purpose of this study was to compare inverted and unprocessed digitized radiographic imaging in periodontal bone loss measurements. Thirty-five film-based periapical radiographs of patients suffering from moderate to advanced untreated periodontal bone loss associated to lower premolar and molars was selected from the department files, with 40 bone loss areas. The film-based radiographs were digitized with a flatbed scanner with a transparency and radiograph adapter used for transilluminating the radiograph imaging. Digitization was performed at 600 dpi and in gray scale. The images were digitized using Image Tool software by applying image inversion, that is, transformation of radiopaque structures into radiolucent structures and vice-versa. The digital data were saved as JPEG files. The images were displayed on a 15-inch and 24-bit video monitor under reduced room lighting. One calibrated examiner performed all radiographic measurements, three times, from the cementoenamel junction to the most apical extension of the bone loss, in both types of image (inverted and unprocessed). Brightness and contrast were adjusted according to the examiner's individual demand. Intraclass correlation coefficient was used to compare the measurements from both types of images. The means of radiographic measurements, in mm, for inverted and unprocessed digitized imaging were 6.4485 and 6.3790, respectively. The intraclass correlation coefficient was significant (0.99) The inverted and unprocessed digitized radiographic images were reliable and there was no difference in the diagnostic accuracy between these images regarding periodontal bone loss measurements.

Bone mineral density on conventional and digitized images under different parameters of digitization and storage

Aim: To assess the bone mineral density on conventional and digitized images, comparing whether different parameters of digitization and storage change these values. Methods: Twenty radiographs were taken from five partially dentulous dry mandibles with an aluminum 7-mm stepwedge placed on the superior edge of the film. After processing, the films were digitized with a resolution of 600 and 2,400 d.p.i. and saved as TIFF and JPEG files. On every conventional and digitized image, circular regions of interest were selected for densitometry and radiographic contrast analysis. Results: Pearson's correlation coefficient showed a significant and strong mean gray values association between digitized and conventional images, differing from radiographic contrast that did not show a significant association. ANOVA did not reveal a statistically significant difference in bone density and radiographic contrast among the four digitized image groups, but the conventional image contrast was significantly lower. Conclusions: Bone mineral density did not differ in both conventional and digitized images. The parameters of image compression and resolution, tested in this study, did not change the results of densitometry and digitization process increased the radiographic contrast.

Eumelanin thin films: Solution-processing, growth, and charge transport properties

Eumelanin pigments show hydration-dependent conductivity, broad-band UV-vis absorption, and chelation of metal ions. Solution-processing of synthetic eumelanins opens new possibilities for the characterization of eumelanin in thin film form and its integration into bioelectronic devices. We investigate the effect of different synthesis routes and processing solvents on the growth, the morphology, and the chemical composition of eumelanin thin films using atomic force microscopy and X-ray photoelectron spectroscopy. We further characterize the films by transient electrical current measurements obtained at 50% to 90% relative humidity, relevant for bioelectronic applications. We show that the use of dimethyl sulfoxide is preferable over ammonia solution as processing solvent, yielding homogeneous films with surface roughnesses below 0.5 nm and a chemical composition in agreement with the eumelanin molecular structure. These eumelanin films grow in a quasi layer-by-layer mode, each layer being composed of nanoaggregates, 1-2 nm high, 10-30 nm large. The transient electrical measurements using a planar two-electrode device suggest that there are two contributions to the current, electronic and ionic, the latter being increasingly dominant at higher hydration, and point to the importance of time-dependent electrical characterization of eumelanin films. This journal is © 2013 The Royal Society of Chemistry.

Reconhecimento de pessoas por meio da região interna da íris

Pós-graduação em Ciência da Computação - IBILCE

Cardiomyopathy and cell therapy: ejection fraction improvement and cardiac muscle mass increasing, after a year of bone marrow stem cells transplantation, by magnetic resonance image

The idiopathic dilated cardiomyopathy (IDC) is one of the major public health problems in the western world. Patients with IDC in functional class IV (New York Health Association - NYHA), even after therapeutic optimization, have high mortality. Stem cell therapy has emerged as a potential therapeutic option for cell death-related heart diseases and several positive effects were assigned to cell therapy in cardiomyopathy. The aim of this study was identify short-term result of cell transplantation in idiopathic dilated cardiomyopathy patients (IDC) who were treated by transplantation of autologous bone marrow mononuclear cells (BMMC). Intracoronary injections of autologous BMMC were performed in eight patients with severe ventricle dysfunction (mean of left ventricle ejection fraction – LEVF=20.03%), cardiac mass muscle around 156.2 g and NYHA between III and IV grades, other 8 IDC patients received placebo. The IDCs were followed - up for one and two years, by magnetic resonance imaging (MRI). The results after one year showed significant improvement in LVEF (mean=181.4) and muscle mass increasing (mean=181.4 g), after two years the LVEF continued improving, reaching a mean of 32.69% and the cardiac muscle mass kept stable (mean=179.4 g). Excepted for one patient, all the other had improvement in the NYHA functional class. The placebo group did not show any improvement. We believe that BMMC implant may be a beneficial therapeutic option for IDC patients.

Sexual Risk Recognition Deficits: The Role of Prior Victimization and Emotion Dysregulation

Recent theoretical writings suggest that the ineffective regulation of negative emotional states may reduce the ability of women to detect and respond effectively to situational and interpersonal factors that increase risk for sexual assault. However, little empirical research has explored this hypothesis. In the present study, it was hypothesized that prior sexual victimization and negative mood state would each independently predict poor risk recognition and less effective defensive actions in response to an analogue sexual assault vignette. Further, these variables were expected to interact to produce particularly impaired risk responses. Finally, that the in vivo emotion regulation strategy of suppression and corresponding cognitive resource usage (operationalized as memory impairment for the vignette) were hypothesized to mediate these associations. Participants were 668 female undergraduate students who were randomly assigned to receive a negative or neutral film mood induction followed by an audiotaped dating interaction during which they were instructed to indicate when the man had “gone too far” and describe an adaptive response to the situation. Approximately 33.5% of the sample reported a single victimization and 10% reported revictimization. Hypotheses were largely unsupported as sexual victimization history, mood condition, and their interaction did not impact risk recognition or adaptive responding. However, in vivo emotional suppression and cognitive resource usage were shown to predict delayed risk recognition only. Findings suggest that contrary to hypotheses, negative mood (as induced here) may not relate to risk recognition and response impairments. However, it may be important for victimization prevention programs that focus on risk perception to address possible underlying issues with emotional suppression and limited cognitive resources to improve risk perception abilities. Limitations and future directions are discussed.