Navegando por Autor "Araújo, Arnaldo de Albuquerque"

Agora exibindo 1 - 9 de 9

Efficient algorithms for hierarchical graph-based segmentation relying on the Felzenszwalb-Huttenlocher dissimilarity.
(2019) Cahuina, Edward Jorge Yuri Cayllahua; Cousty, Jean; Kenmochi, Yukiko; Araújo, Arnaldo de Albuquerque; Cámara Chávez, Guillermo; Guimarães, Silvio Jamil Ferzoli
Hierarchical image segmentation provides a region-oriented scale-space, i.e. a set of image segmentations at different detail levels in which the segmentations at finer levels are nested with respect to those at coarser levels. However, most image segmentation algorithms, among which a graph-based image segmentation method relying on a region merging criterion was proposed by Felzenszwalb–Huttenlocher in 2004, do not lead to a hierarchy. In order to cope with a demand for hierarchical segmentation, Guimarães et al. proposed in 2012 a method for hierarchizing the popular Felzenszwalb–Huttenlocher method, without providing an algorithm to compute the proposed hierarchy. This paper is devoted to providing a series of algorithms to compute the result of this hierarchical graph-based image segmentation method efficiently, based mainly on two ideas: optimal dissimilarity measuring and incremental update of the hierarchical structure. Experiments show that, for an image of size 321 × 481 pixels, the most efficient algorithm produces the result in half a second whereas the most naive one requires more than 4 h.
Fast hue-preserving histogram equalization methods for color image contrast enhancement.
(2012) Gomes, David Menotti; Najman, Laurent; Facon, Jacques; Araújo, Arnaldo de Albuquerque
In this work, we formalize a generic fast hue-preserving histogram equalization method based on the RGB color space for image contrast enhancement and two versions of that generic process. The first method estimates a RGB 3D histogram to be equalized using R-red, G-green, and B-blue 1D histograms, while the second method employs RG, RB, and GB 2D histograms. The histogram equalization is performed using shift hue-preserving transformations, avoiding unrealistic colors. Our methods have linear time and space complexities with respect to the size of the image and do not need to apply conversions from a color space to another in order to perform the image enhancement. Such design complies with real-time applications requirements. An objective assessment comparing our methods and others is performed using a contrast measure and a color image quality measure, where the quality is established as a weighting of the naturalness and colorfulness indexes. We analyze 300 images from the dataset of the University of Berkeley. Experiments show that the value of the image contrast produced by our methods is in average 50% greater than the original image value, keeping the quality of the produced images close to the original one.
Hierarchical segmentation from a non-increasing edge observation attribute.
(2019) Cayllahua Cahuina, Edward Jorge Yuri; Cousty, Jean; Guimarães, Silvio Jamil Ferzoli; Kenmochi, Yukiko; Cámara Chávez, Guillermo; Araújo, Arnaldo de Albuquerque
Hierarchical image segmentation provides region-oriented scale-spaces: sets of image segmentations at different detail levels in which the segmentations at finer levels are nested with respect to those at coarser levels. Guimaraes ˜ et al. proposed a hierarchical graph-based image segmentation (HGB) method based on the Felzenszwalb-Huttenlocher dissimilarity. It computes, for each edge of a graph, the minimum scale in a hierarchy at which two regions linked by this edge should be merged according to the dissimilarity. We provide an explicit definition of the (edge-) observation attribute and Boolean criterion which are at the basis of this method and show that they are not increasing. Then, we propose an algorithm to compute all the scales for which the criterion holds true. Finally, we propose new methods to regularize the observation attribute and criterion and to set up the observation scale value of each edge of a graph, following the current trend in mathematical morphology to study criteria which are not increasing on a hierarchy. Assessments on Pascal VOC 2010 and 2012 show that these strategies lead to better segmentation results than the ones obtained with the original HGB method.
MammoSys : a content-based image retrieval system using breast density patterns.
(2010) Oliveira, Júlia E. E.; Machado, Alexei M. C.; Cámara Chávez, Guillermo; Lopes, Ana Paula B.; Deserno, Thomas N.; Araújo, Arnaldo de Albuquerque
In this paper, we present a content-based image retrieval system designed to retrieve mammographies from large medical image database. The system is developed based on breast density, according to the four categories defined by the American College of Radiology, and is integrated to the database of the Image Retrieval in Medical Applications (IRMA) project, that provides images with classification ground truth. Two-dimensional principal component analysis is used in breast density texture characterization, in order to effectively represent texture and allow for dimensionality reduction. A support vector machine is used to perform the retrieval process. Average precision rates are in the range from 83% to 97% considering a data set of 5024 images. The results indicate the potential of the system as the first stage of a computer-aided diagnosis framework.
A methodology for photometric validation in vehicles visual interactive systems.
(2012) Faria, Alexandre Wagner Chagas; Menotti, David; Pappa, Gisele Lobo; Lara, Daniel da Silva Diogo; Araújo, Arnaldo de Albuquerque
This work proposes a methodology for automatically validating the internal lighting system of an automobile by assessing the visual quality of each instrument in an instrument cluster (IC) (i.e., vehicle gauges, such as speedometer, tachometer, temperature and fuel gauges) based on the user’s perceptions. Although the visual quality assessment of an instrument is a subjective matter, it is also influenced by some of its photometric features, such as the light intensity distribution. This work presents a methodology for identifying and quantifying non-homogeneous regions in the lighting distribution of these instruments, starting from a digital image. In order to accomplish this task, a set of 107 digital images of instruments were acquired and preprocessed, identifying a set of instrument regions. These instruments were also evaluated by common drivers and specialists to identify their non-homogenous regions. Then, for each region, we extracted a set of homogeneity descriptors, and also proposed a relational descriptor to study the homogeneity influence of a region in the whole instrument. These descriptors were associated with the results of the manual labeling, and given to two machine learning algorithms, which were trained to identify a region as being homogeneous or not. Experiments showed that the proposed methodology obtained an overall precision above 94% for both regions and instrument classifications. Finally, a meticulous analysis of the users’ and specialist’s image evaluations is performed
Uma metodologia para validação fotométrica em sistemas interativos visuais baseada em inteligência computacional.
(2009) Faria, Alexandre Wagner Chagas; Lara, Daniel da Silva Diogo; Araújo, Arnaldo de Albuquerque; Gomes, David Menotti
Neste artigo, é apresentada uma metodologia automática para a validação fotométrica em sistemas de iluminação interna veicular. Nessa metodologia, propõe-se um método para extração de descritores de homogeneidade de cada região de avaliação. A percepção visual humana, representada pela avaliação do usuário, é usada para classificar as regiões em homogêneas e não-homogêneas. Dois algoritmos de aprendizado de máquina (Redes neurais e Support Vector Machine) são usados para a classificação de regiões visando identificar quais as melhores configurações de descritores irá representar a percepção do usuário em relação à homogeneidade da iluminação dos sistemas de interação com o motorista. Resultados experimentais mostram que a metodologia proposta consegue diferenciar regiões homogêneas de não-homogêneas com precisão superior á 90%.
Multi-histogram equalization methods for contrast enhancement and brightness preserving.
(2007) Menotti, David; Najman, Laurent; Facon, Jacques; Araújo, Arnaldo de Albuquerque
Histogram equalization (HE) has proved to be a simple and effective image contrast enhancement technique. However, it tends to change the mean brightness of the image to the middle level of the gray-level range, which is not desirable in the case of images from consumer electronics products. In the latter case, preserving the input brightness of the image is required to avoid the generation of non-existing artifacts in the output image. To surmount this drawback, Bi- HE methods for brightness preserving and contrast enhancement have been proposed. Although these methods preserve the input brightness on the output image with a significant contrast enhancement, they may produce images with do not look as natural as the input ones. In order to overcome this drawback, this work proposes a novel technique called Multi-HE, which consists of decomposing the input image into several sub-images, and then applying the classical HE process to each one. This methodology performs a less intensive image contrast enhancement, in a way that the output image presents a more natural look. We propose two discrepancy functions for image decomposing, conceiving two new Multi-HE methods. A cost function is also used for automatically deciding in how many sub-images the input image will be decomposed on. Experiments show that our methods preserve more the brightness and produce more natural looking images than the other HE methods.
A novel hybrid method for the segmentation of the coronary artery tree in 2D angiograms.
(2013) Lara, Daniel da Silva Diogo; Faria, Alexandre Wagner Chagas; Araújo, Arnaldo de Albuquerque; Gomes, David Menotti
Nowadays, medical diagnostics using images have considerable importance in many areas of medicine. Specifically, diagnoses of cardiac arteries can be performed by means of digital images. Usually, this diagnostic is aided by computational tools. Generally, automated tools designed to aid in coronary heart diseases diagnosis require the coronary artery tree segmentation. This work presents a method for a semiautomatic segmentation of the coronary artery tree in 2D angiograms. In other to achieve that, a hybrid algorithm based on region growing and differential geometry is proposed. For the validation of our proposal, some objective and quantitative metrics are defined allowing us to compare our method with another one proposed in the literature. From the experiments, we observe that, in average, the proposed method here identifies about 90% of the coronary artery tree while the method proposed by Schrijver & Slump (2002) identifies about 80%.
Smooth surface reconstruction using tensor fields as structuring elements.
(2004) Vieira, Marcelo Bernarde; Martins Júnior, Paulo Pereira; Araújo, Arnaldo de Albuquerque; Cord, Matthieu; Foliguet, Sylvie Philipp
We propose a new strategy to estimate surface normal information from highly noisy sparse data. Our approach is based on a tensor field morphologically adapted to infer normals. It acts as a three-dimensional structuring element of smooth surfaces. Robust orientation inference for all input elements is performed by morphological operations using the tensor field. A general normal estimator is defined by combining the inferred normals, their confidences and the tensor field. This estimator can be used to directly reconstruct the surface or give input normals to other reconstruction methods.We present qualitative and quantitative results to show the behavior of the original methods and ours. A comparative discussion of these results shows the efficiency of our propositions.