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.

Evaluation epidermal p53 immunostaining by digital image analysis

Digital techniques have been developed and validated to assess semiquantitatively immunohistochemical nuclear staining. Currently visual classification is the standard for qualitative nuclear evaluation. Analysis of pixels that represents the immunohistochemical labeling can be more sensitive, reproducible and objective than visual grading. This study compared two semiquantitative techniques of digital image analysis with three techniques of visual analysis imaging to estimate the p53 nuclear immunostaining. Methods: Sixty-three sun-exposed forearm-skin biopsies were photographed and submitted to three visual analyses of images: the qualitative visual evaluation method (0 to 4 +), the percentage of labeled nuclei and HSCORE. Digital image analysis was performed using ImageJ 1.45p; the density of nuclei was scored per ephitelial area (DensNU) and the pixel density was established in marked suprabasal epithelium (DensPSB). Results: Statistical significance was found in: the agreement and correlation among the visual estimates of evaluators, correlation among the median visual score of the evaluators, the HSCORE and the percentage of marked nuclei with the DensNU and DensPSB estimates. DensNU was strongly correlated to the percentage of p53-marked nuclei in the epidermis, and DensPSB with the HSCORE. Conclusion: The parameters presented herein can be applied in routine analysis of immunohistochemical nuclear staining of epidermis. © 2012 John Wiley & Sons A/S.

Enzyme use in kibble diets formulated with wheat bran for dogs: Effects on processing and digestibility

Recently, there is an interest in technologies that favour the use of coproducts for animal nutrition. The effect of adding two enzyme mixtures in diets for dogs formulated with wheat bran (WB) was evaluated. Two foods with similar compositions were formulated: negative control (NC; without WB) and test diet (25% of WB). The test diet was divided into four treatments: without enzyme (positive control), enzyme mixture 1 (ENZ1; added before extrusion β-glucanase, xylanase, cellulase, glucoamylase, phytase); enzyme mixture 2 (ENZ2; added before extrusion the ENZ1 more α-amylase); enzyme mixture 2 added after the extrusion (ENZ2ex). ENZ1 and ENZ2 were used to evaluate the enzyme effect on extruder pre-conditioner (processing additive) and ENZ2ex to evaluate the effect of enzyme supplementation for the animal. Digestibility was measured through total collection of faeces and urine. The experiment followed a randomized block design with five treatments (diets) and six dogs per diet, totalling 30 dogs (7.0 ± 1.2 years old and 11.0 ± 2.2 kg of body weight). Data were submitted to analysis of variance and means compared by Tukey's test and orthogonal contrasts (p < 0.05). Reducing sugars showed an important reduction after extrusion, suggesting the formation of carbohydrate complexes. The apparent total tract digestibility (ATTD) of dry matter, organic matter, crude protein, acid-hydrolysed fat and energy was higher in NC than in diets with WB (p < 0.001), without effects of enzyme additions. WB diets resulted in higher faecal production and concentration of short-chain fatty acids (SCFA) and reduced pH and ammonia concentration (p < 0.01), with no effect of enzyme addition. The enzyme addition did not result in improved digestibility of a diet high in non-starch polysaccharides; however, only ATTD was measured and nutrient fermentation in the large intestine may have interfered with the results obtained. WB modified fermentation product formation in the colon of dogs. © 2013 Blackwell Verlag GmbH.

Effects of pre-slaughter fasting on broiler welfare, meat quality, and intestinal integrity

The Brazilian Ministry of Agriculture (MAPA) regulations establish 12 hours as the maximum pre-slaughter fasting period for broilers; however, many processing plants have considered this time is not sufficient, and consequently return the birds to the farms, with consequent economic losses and welfare problems. Therefore, it is necessary to investigate the possible effects of longer pre-slaughter fasting times. The objective of the present study was to evaluate the effect of pre-slaughter fasting times longer than those established by MAPA on broiler welfare, breast meat quality, and intestinal integrity. Forty 42-d-old broilers were submitted to different pre-slaughter fasting times: group I: 6 hours, group II 9h, group III 12h, and group IV 15h. Bird welfare was assessed before slaughter. After sacrifice, intestinal samples were collected to assess their morphology and morphometrics, and the Pectoralis major muscle was analyzed for pH and color. There was no influence (p>0.05) of treatments on breast muscle pH or color.There were no significant changes in intestinal morphometrics (p<0.05). Bird behavior was affected (p<0.05), suggesting that welfare was impaired as fasting time increased, but no differences in the analyzed parameters were detected between broilers fasted for 12 or 15 hours. It was concluded that the behavioral differences between birds fasted for 12 and 15 hours are not sufficient to assert that those fasted for 15 hours were in worse welfare conditions.

Análise dos sprays de jatos de injetores de motor foguete utilizando um sistema de processamento digital de imagens

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Migração em profundidade pré-empilhamento utilizando os atributos cinemáticos do empilhamento por superfície de reflexão comum

O empilhamento por superfície de reflexão comum (ou empilhamento SRC), conhecido como empilhamento CRS, do inglês Commom reflection surface, constitui-se em um novo método para o processamento sísmico na simulação de seções afastamento nulo (AN) e afastamento comum (AC). Este método é baseado em uma aproximação paraxial hiperbólica de segunda ordem dos tempos de trânsito de reflexão na vizinhança de um raio central. Para a simulação de seção AN, o raio central é um raio normal, enquanto que para a simulação de uma seção AC o raio central é um raio de afastamento finito. Em adição à seção AN, o método de empilhamento SRC também fornece estimativas dos atributos cinemáticos do campo de onda, sendo aplicados, por exemplo, na determinação (por um processo de inversão) da velocidade intervalar, no cálculo do espalhamento geométrico, na estimativa da zona de Fresnel, e também na simulação de eventos de tempos de difrações, este último tendo uma grande importância para a migração pré-empilhamento. Neste trabalho é proposta uma nova estratégia para fazer uma migração em profundidade pré-empilhamento, que usa os atributos cinemáticos do campo de onda derivados do empilhamento SRC, conhecido por método CRS-PSDM, do inglês CRS based pre-stack depth migration. O método CRS-PSDM usa os resultados obtidos do método SRC, isto é, as seções dos atributos cinemáticos do campo de onda, para construir uma superfície de tempos de trânsito de empilhamento, ao longo da qual as amplitudes do dado sísmico de múltipla cobertura são somadas, sendo o resultado da soma atribuído a um dado ponto em profundidade, na zona alvo de migração que é definida por uma malha regular. Similarmente ao método convencional de migração tipo Kirchhoff (K-PSDM), o método CRS-PSDM precisa de um modelo de velocidade de migração. Contrário ao método K-PSDM, o método CRS-PSDM necessita apenas computar os tempos de trânsito afastamento nulo, ao seja, ao longo de um único raio ligando o ponto considerado em profundidade a uma dada posição de fonte e receptor coincidentes na superfície. O resultado final deste procedimento é uma imagem sísmica em profundidade dos refletores a partir do dado de múltipla cobertura.

Estudo das feições lineares observadas em dados aeromagnéticos da Bacia do Solimões a partir de imagens digitais de sombreamento do relevo anômalo total

A Bacia do Solimões é caracterizada por um padrão magnético complexo, expresso ao longo de toda sua extensão, e produzido pela superposição de anomalias magnéticas que se apresentam sob a forma de feições lineares. Tais feições refletem as diferentes atividades tectônicas que atuaram na Região Amazônica através do Pré-Cambriano e Fanerozóico. Neste trabalho, foi aplicado nos dados aeromagnéticos da Bacia do Solimões um método de processamento de imagens digitais de sombreamento do relevo magnético anômalo total que, dadas suas características metodológicas, permitindo utilizá-lo como um filtro direcional, possibilitou a definição de aspectos relevantes no contexto das relações entre os lineamentos magnéticos E/W, NE/SW, e NW/SE. Nesse sentido, foram identificados padrões de lineamentos magnéticos que refletem a existência de zonas de cisalhamento transcorrentes dextrais, orientadas preferencialmente na direção E/W. A interação entre os diversos segmentos transcorrentes promoveu o desenvolvimento de um regime predominantemente transpressivo, representado por falhas reversas associadas aos lineamentos magnéticos E/W e NE/SW; e duplexes direcionais formando falhas em flor positivas e negativas associadas, respectivamente, aos lineamentos magnéticos orientados na direção N70-80E e N70-80W. A análise quantitativa permitiu explicar dois aspectos importantes em relação às feições lineares observadas nas imagens digitais. O primeiro mostra, através de modelamentos baseados na superposição de prismas bidimensionais, que estas feições lineares magnéticas podem ser explicadas pela superposição de fontes profundas intraembasamento altamente magnéticas, e fontes rasas de alta frequência, sendo estas associadas a falhas reversas ao longo dos níveis de diabásio, presentes em forma de intrusões nos sedimentos paleozóicos da Bacia do Solimões. O segundo aspecto, baseado na utilização dos conceitos da cross-covariância, constata a presença de 'offsets' dextrais, associados aos lineamentos magnéticos NE—SW, ao longo da direção E—W. Este fato mostra, quantitativamente, que o padrão magnético desta região pode ser explicado pela presença de zonas de cisalhamento transcorrestes dextrais, cujos processos tectônicos associados foram fortemente condicionados por zonas de fraquezas pré-existentes (Pré-Cambrianas, Paleozóicas) durante o Mesozóico e Cenozóico.

Application of two segmentation protocols during the processing of virtual images in rapid prototyping: ex vivo study with human dry mandibles

The aim of this study was to evaluate the accuracy of virtual three-dimensional (3D) reconstructions of human dry mandibles, produced from two segmentation protocols (outline only and all-boundary lines).Twenty virtual three-dimensional (3D) images were built from computed tomography exam (CT) of 10 dry mandibles, in which linear measurements between anatomical landmarks were obtained and compared to an error probability of 5 %.The results showed no statistically significant difference among the dry mandibles and the virtual 3D reconstructions produced from segmentation protocols tested (p = 0,24).During the designing of a virtual 3D reconstruction, both outline only and all-boundary lines segmentation protocols can be used.Virtual processing of CT images is the most complex stage during the manufacture of the biomodel. Establishing a better protocol during this phase allows the construction of a biomodel with characteristics that are closer to the original anatomical structures. This is essential to ensure a correct preoperative planning and a suitable treatment.

Unsupervised manifold learning using Reciprocal kNN Graphs in image re-ranking and rank aggregation tasks

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Pre-extrusion aromatization of a soy protein isolate using volatile compounds and flavor enhancers: Effects on physical characteristics, volatile retention and sensory characteristics of extrudates

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Image Re-Ranking Acceleration on GPUs

Huge image collections are becoming available lately. In this scenario, the use of Content-Based Image Retrieval (CBIR) systems has emerged as a promising approach to support image searches. The objective of CBIR systems is to retrieve the most similar images in a collection, given a query image, by taking into account image visual properties such as texture, color, and shape. In these systems, the effectiveness of the retrieval process depends heavily on the accuracy of ranking approaches. Recently, re-ranking approaches have been proposed to improve the effectiveness of CBIR systems by taking into account the relationships among images. The re-ranking approaches consider the relationships among all images in a given dataset. These approaches typically demands a huge amount of computational power, which hampers its use in practical situations. On the other hand, these methods can be massively parallelized. In this paper, we propose to speedup the computation of the RL-Sim algorithm, a recently proposed image re-ranking approach, by using the computational power of Graphics Processing Units (GPU). GPUs are emerging as relatively inexpensive parallel processors that are becoming available on a wide range of computer systems. We address the image re-ranking performance challenges by proposing a parallel solution designed to fit the computational model of GPUs. We conducted an experimental evaluation considering different implementations and devices. Experimental results demonstrate that significant performance gains can be obtained. Our approach achieves speedups of 7x from serial implementation considering the overall algorithm and up to 36x on its core steps.

Comportamento fractal de superfície da zona de estiramento em aço 300M temperado

Fracture surfaces are the fracture process marks, taht it is characterized by energy release guieded by failure mode. The fracture toughness express this energy em stress and strain terms in pre-cracked samples. The strectch zone is the characteristic region forms by the transition of fatigue fracture and final fracture and it width demonstrate the relation with failure energy release.The quantitative fractography is a broadly tool uses in failure surfaces characterization that it can point to a material’s aspect or a fracture process. The image processing works like an investigation tool, guinding a lot of studies in this area. In order to evaluate the characterization effectivity and it respectivity studies, it used 300M steel that it was thermal treated by an aeronautical process known and it characterized by tensile test and energy dispersive spectroscopy (EDS). The tensile test of this material, made by ASTM E8, allowed the head treatment effectivity confirmation, beyond of mechanics porperties determination. The EDS confirmed the material composition, beyond of base the discussion about fracture mechanism presence. The fracture toughness test has also made, that it works to obtain the fracture surfeaces studies below self-similarity and self-affinity approaches. In front of all the exposed it was possible to conclude that the fractal dimension works like a study parameter of fracture process, allowinf the relation of their values with changes in thickness, which interferes directly in material’s behaviour in fracture toughness approach

Effect of digitization parameters on periapical radiographic image quality with regard to anatomic landmarks

The aim of this study was to evaluate the influence of digitization parameters on periapical radiographic image quality, with regard to anatomic landmarks. Digitized images (n = 160) were obtained using a flatbed scanner with resolutions of 300, 600 and 2400 dpi. The radiographs of 2400 dpi were decreased to 300 and 600 dpi before storage. Digitizations were performed with and without black masking using 8-bit and 16-bit grayscale and saved in TIFF format. Four anatomic landmarks were classified by two observers (very good, good, moderate, regular, poor), in two random sessions. Intraobserver and interobserver agreements were evaluated by Kappa statistics. Inter and intraobserver agreements ranged according to the anatomic landmarks and resolution used. The results obtained demonstrated that the cement enamel junction was the anatomic landmark that presented the poorest concordance. The use of black masking provided better results in the digitized image. The use of a mask to cover radiographs during digitization is necessary. Therefore, the concordance ranged from regular to moderate for the intraobserver evaluation and concordance ranged from regular to poor for interobserver evaluation.

Comparative analysis of three rotary instruments used for coronal pre-enlargement in radicular dentin thickness and root canal area of mandibular molars

Purpose: The purpose of this study was to evaluate the increase of the cervical area and dentin thickness in mesial and distal walls of the mesial canals from mandibular molars after the use of LA Axxess (LA), CP Drill (CP) and Gates-Glidden (GG) rotary instruments. Material and Methods: Sixty root canals from thirty mandibular first molar were sectioned 3 mm below the cement-enamel junction, divided in 3 groups (n = 20 root canals, each) according to rotary instrument used, and the cervical images were captured before and after pre-enlargement instrumentation. The increase of the instrumented cervical area (mm2) and the dentin removal thickness (mm), at mesial and distal walls were calculated using Image tools software, by comparison of images. Data were analyzed by ANOVA and Tukey tests (p=0.05). Results: All rotary instruments promoted thickness reduction in dentin walls. In mesial wall, all rotary instruments promoted similar thickness reduction of dentinal wall and did not differ from each other (p>0.05). In distal wall, LA Axxess instrument promoted higher dentin thickness reduction than other groups (p<0.05). The three rotary instruments promoted different increase at the instrumented cervical area (p<0.05), LA promoted the highest increase area and GG and CP presented similar results. Conclusion: LA 20/0.06 promoted the highest thickness reduction in distal wall and increase of cervical area of root canal. On the other hand, CP was the safest instrument, with lower dentin removal of distal wall and similar increased area to GG.

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.