Limiarização contextual automática de imagens coloridas: aplicação na extração de sementes de rodovia

In this paper is a totally automatic strategy proposed to reduce the complexity of patterns ( vegetation, building, soils etc.) that interact with the object 'road' in color images, thus reducing the difficulty of the automatic extraction of this object. The proposed methodology consists of three sequential steps. In the first step the punctual operator is applied for artificiality index computation known as NandA ( Natural and Artificial). The result is an image whose the intensity attribute is the NandA response. The second step consists in automatically thresholding the image obtained in the previous step, resulting in a binary image. This image usually allows the separation between artificial and natural objects. The third step consists in applying a preexisting road seed extraction methodology to the previous generated binary image. Several experiments carried out with real images made the verification of the potential of the proposed methodology possible. The comparison of the obtained result to others obtained by a similar methodology for road seed extraction from gray level images, showed that the main benefit was the drastic reduction of the computational effort.

Fractal descriptors for discrimination of microscopy images of plant leaves

This study proposes the application of fractal descriptors method to the discrimination of microscopy images of plant leaves. Fractal descriptors have demonstrated to be a powerful discriminative method in image analysis, mainly for the discrimination of natural objects. In fact, these descriptors express the spatial arrangement of pixels inside the texture under different scales and such arrangements are directly related to physical properties inherent to the material depicted in the image. Here, we employ the Bouligand-Minkowski descriptors. These are obtained by the dilation of a surface mapping the gray-level texture. The classification of the microscopy images is performed by the well-known Support Vector Machine (SVM) method and we compare the success rate with other literature texture analysis methods. The proposed method achieved a correctness rate of 89%, while the second best solution, the Co-occurrence descriptors, yielded only 78%. This clear advantage of fractal descriptors demonstrates the potential of such approach in the analysis of the plant microscopy images.

On the efficacy of texture analysis for crowd monitoring

The goal of this work is to assess the efficacy of texture measures for estimating levels of crowd densities ill images. This estimation is crucial for the problem of crowd monitoring. and control. The assessment is carried out oil a set of nearly 300 real images captured from Liverpool Street Train Station. London, UK using texture measures extracted from the images through the following four different methods: gray level dependence matrices, straight lille segments. Fourier analysis. and fractal dimensions. The estimations of dowel densities are given in terms of the classification of the input images ill five classes of densities (very low, low. moderate. high and very high). Three types of classifiers are used: neural (implemented according to the Kohonen model). Bayesian. and an approach based on fitting functions. The results obtained by these three classifiers. using the four texture measures. allowed the conclusion that, for the problem of crowd density estimation. texture analysis is very effective.

Um estudo sobre o osu do modelo de cor RGB no proceso de correspondência por correlação

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

Border detection in digital images: An approach by fuzzy numbers

The purpose of this paper is to introduce a new approach for edge detection in gray shaded images. The proposed approach is based on the fuzzy number theory. The idea is to deal with the uncertainties concerning the gray shades making up the image, and thus calculate the appropriateness of the pixels in relation to an homogeneous region around them. The pixels not belonging to the region are then classified as border pixels. The results have shown that the technique is simple, computationally efficient and with good results when compared with both the traditional border detectors and the fuzzy edge detectors. © 2007 IEEE.

Técnicas de correlação no delineamento de feições rodoviárias em imagens de baixa e média resolução

This paper presents a method for the sequential road feature delineation from digital images. It is based on a feedback loop between extrapolation and refinement steps of a given road centerline point, using in both steps correlation techniques. Firstly, a previously extracted road centerline point is linearly extrapolated, resulting in an approximate position. Secondly, this approximate position is corrected by comparing gray level profiles extracted perpendicularly to the extrapolation direction. This strategy is then repeated to allow the entire road centerline to be extracted or a stop point to be found. In order to initialize the extraction process, the operator needs to supply a starting point plus direction and width. Experimental results obtained from the application of the method to real image data are presented and discussed in this paper.

Análise da incerteza na representação de classes temáticas resultantes da aplicação de uma rede neural artificial

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Estudo de métodos para classificação e localização precisa de padrões usando um sistema de luz estruturada

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Instantaneous Phase Threshold for Reflector Detection in Ultrasonic Images

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

Segmentação de texturas em imagens digitais utilizando wavelets redundantes

Pós-graduação em Matematica Aplicada e Computacional - FCT

The influence of ovariectomy, simvastatin and sodium alendronate on alveolar bone in rats

Bisphosphonates are currently used in the treatment of many diseases involving increased bone resorption such as osteoporosis. Statins have been widely used for the treatment of hypercholesterolemia and recent studies have shown that these drugs are also capable of stimulating bone formation. The purpose of this study was to evaluate thel influence of an estrogen deficient state and the effects of simvastatin and sodium alendronate therapies on alveolar bone in female rats. Fifty-four rats were either ovariectomized (OVX) or sham operated. A month later, the animals began to receive a daily dose of simvastatin (SIN - 25 mg/kg), sodium alendronate (ALN - 2 mg/kg) or water (control) orally. Thirty-five days after the beginning of the treatment, the rats were sacrificed and their left hemimandibles were removed and radiographed using digital X-ray equipment. The alveolar radiographic density under the first molar was determined with gray-level scaling and the values were submitted to analysis of variance (α = 5%). Ovariectomized rats gained more weight (mean ± standard deviation: 20.06 ± 6.68%) than did the sham operated animals (12.13 ± 5.63%). Alveolar radiographic density values, expressed as gray levels, were lowest in the OVX-water group (183.49 ± 6.47), and differed significantly from those observed for the groups receiving alendronate (sham-ALN: 193.85 ± 3.81; OVX-ALN: 196.06 ± 5.11) and from those of the sham-water group (193.66 ± 4.36). Other comparisons between groups did not show significant differences. It was concluded that the ovariectomy reduced alveolar bone density and that alendronate was efficient for the treatment of this condition.

Avaliação da influência da velocidade de perfuração na reabsorção óssea ao redor de implantes osseointegrados instalados por meio de cirurgia guiada sem retalho: estudo clínico, radiográfico e histológico

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Determinação da qualidade da radiografia digital aplicada às soldas de gasodutos e oleodutos terrestres e marítimos

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Fluorescence Level of Composites Assessed by Computer Processing of Digital Images - ScanWhite

The human dentition is naturally translucent, opalescent and fluorescent. Differences between the level of fluorescence of tooth structure and restorative materials may result in distinct metameric properties and consequently perceptible disparate esthetic behavior, which impairs the esthetic result of the restorations, frustrating both patients and staff. In this study, we evaluated the level of fluorescence of different composites (Durafill in tones A2 (Du), Charisma in tones A2 (Ch), Venus in tone A2 (Ve), Opallis enamel and dentin in tones A2 (OPD and OPE), Point 4 in tones A2 (P4), Z100 in tones A2 ( Z1), Z250 in tones A2 (Z2), Te-Econom in tones A2 (TE), Tetric Ceram in tones A2 (TC), Tetric Ceram N in tones A1, A2, A4 (TN1, TN2, TN4), Four seasons enamel and dentin in tones A2 (and 4SD 4SE), Empress Direct enamel and dentin in tones A2 (EDE and EDD) and Brilliant in tones A2 (Br)). Cylindrical specimens were prepared, coded and photographed in a standardized manner with a Canon EOS digital camera (400 ISO, 2.8 aperture and 1/ 30 speed), in a dark environment under the action of UV light (25 W). The images were analyzed with the software ScanWhite©-DMC/Darwin systems. The results showed statistical differences between the groups (p < 0.05), and between these same groups and the average fluorescence of the dentition of young (18 to 25 years) and adults (40 to 45 years) taken as control. It can be concluded that: Composites Z100, Z250 (3M ESPE) and Point 4 (Kerr) do not match with the fluorescence of human dentition and the fluorescence of the materials was found to be affected by their own tone.

Application of wavelets to the evaluation of phantom images for mammography quality control

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)