Main Publications

2021

Towards Providing Effective Data-Driven Responses to Predict the Covid-19 in São Paulo and Brazil

F. Amaral, W. Casaca, C.M. Oishi, J.A. Cuminato

Sensors

São Paulo is the most populous state in Brazil, home to around 22% of the country’s population. The total number of Covid-19-infected people in São Paulo has reached more than 1 million, while its total death toll stands at 25% of all the country’s fatalities. Joining the Brazilian academia efforts in the fight against Covid-19, in this paper we describe a unified framework for monitoring and forecasting the Covid-19 progress in the state of São Paulo. More specifically, a freely available, online platform to collect and exploit Covid-19 time-series data is presented, supporting decision-makers while still allowing the general public to interact with data from different regions of the state. Moreover, a novel forecasting data-driven method has also been proposed, by combining the so-called Susceptible-Infectious-Recovered-Deceased model with machine learning strategies to better fit the mathematical model’s coefficients for predicting Infections, Recoveries, Deaths, and Viral Reproduction Numbers. We show that the obtained predictor is capable of dealing with badly conditioned data samples while still delivering accurate 10-day predictions. Our integrated computational system can be used for guiding government actions mainly in two basic aspects: real-time data assessment and dynamic predictions of Covid-19 curves for different regions of the state. We extend our analysis and investigation to inspect the virus spreading in Brazil in its regions. Finally, experiments involving the Covid-19 advance in other countries are also given. View Full-Text

2020

A High-Order Immersed Interface Method Free of Derivative Jump Conditions for Poisson Equations on Irregular Domains

M. Colnago, W. Casaca, L.F. Souza

Journal of Computational Physics

Immersed Interface Methods (IIM) arise as a very effective tool to solve many interface problems encountered in fluid dynamics, mechanics and other related fields of study. Despite their versatility and potential, IIM-inspired techniques impose as constraints different types of jump conditions in order to be mathematically tractable and usable in practice. To cope with this issue, in this paper we introduce a novel Immersed Interface method for solving Poisson equations with discontinuous coefficients on Cartesian grids. Different from most conventional methods which assume some derivative information at the interface to produce a valid approximation, our approach reduces the number of regular constraints when solving the Poisson problem, requiring to be given only the ordinary jumps of the function. We combine Finite Difference schemes, ghost node strategy, correction formulas, and interpolation rules into a unified and stable numerical model. Moreover, the present method is capable of producing high-order solutions from a unique resource of available data. We attest to the accuracy and robustness of our single jump-based method through a variety of numerical experiments comprising Poisson problems with interfaces that can be now solved from a reduced number of jump conditions.

Spectral-Spatial-Aware Unsupervised Change Detection with Stochastic Distances and Support Vector Machines

R.G. Negri, A.C. Frery, W. Casaca, S. Azevedo, M. A. Dias, E.A. Silva, E.H. Alcântara

IEEE Transactions on Geoscience and Remote Sensing (accepted - early access)

Change detection is a topic of great interest in remote sensing. A good similarity metric to compute the variations among the images is the key to high-quality change detection. However, most existing approaches rely on the fixed threshold values or the user-provided ground truth in order to be effective. The inability to deal with artificial objects such as clouds and shadows is a significant difficulty for many change-detection methods. We propose a new unsupervised change-detection framework to address those critical points. The notion of homogeneous regions is introduced together with a set of geometric operations and statistic-based criteria to characterize and distinguish formally the change and nonchange areas in a pair of remote sensing images. Moreover, a robust and statistically well-posed family of stochastic distances is also proposed, which allows comparing the probability distributions of different regions/objects in the images. These stochastic measures are then used to train a support-vector-machine-based approach in order to detect the change/nonchange areas. Three study cases using the images acquired with different sensors are given in order to compare the proposed method with other well-known unsupervised methods.

Laplacian Coordinates: Theory and Methods for Seeded Image Segmentation

W. Casaca, J.P. Gois, H.C. Batagelo, G. Taubin, L.G. Nonato

IEEE Transactions on Pattern Analysis and Machine Intelligence (accepted - early access)

Seeded segmentation methods have gained a lot of attention due to their good performance in fragmenting complex images, easy usability and synergism with graph-based representations. These methods usually rely on sophisticated computational tools whose performance strongly depends on how good the training data reflect a sought image pattern. Moreover, poor adherence to the image contours, lack of unique solution, and high computational cost are other common issues present in most seeded segmentation methods. In this work we introduce Laplacian Coordinates, a quadratic energy minimization framework that tackles the issues above in an effective and mathematically sound manner. The proposed formulation builds upon graph Laplacian operators, quadratic energy functions, and fast minimization schemes to produce highly accurate segmentations. Moreover, the presented energy functions are not prone to local minima, i.e., the solution is guaranteed to be globally optimal, a trait not present in most image segmentation methods. Another key property is that the minimization procedure leads to a constrained sparse linear system of equations, enabling the segmentation of high-resolution images at interactive rates. The effectiveness of Laplacian Coordinates is attested by a comprehensive set of comparisons involving nine state-of-the-art methods and several benchmarks extensively used in the image segmentation literature.

Towards Assessing the Electricity Demand in Brazil: Data-Driven Analysis and Ensemble Learning Models

J.V. Leme, W. Casaca, M. Colnago, M.A. Dias

Energies

The prediction of electricity generation is one of the most important tasks in the management of modern energy systems. Improving the assertiveness of this prediction can support government agencies, electric companies, and power suppliers in minimizing the electricity cost to the end consumer. In this study, the problem of forecasting the energy demand in the Brazilian Interconnected Power Grid was addressed, by gathering different energy-related datasets taken from public Brazilian agencies into a unified and open database, used to tune three machine learning models. In contrast to several works in the Brazilian context, which provide only annual/monthly load estimations, the learning approaches Random Forest, Gradient Boosting, and Support Vector Machines were trained and optimized as new ensemble-based predictors with parameter tuning to reach accurate daily/monthly forecasts. Moreover, a detailed and in-depth exploration of energy-related data as obtained from the Brazilian power grid is also given. As shown in the validation study, the tuned predictors were effective in producing very small forecasting errors under different evaluation scenarios.

An Incongruence-Based Anomaly Detection Strategy for Analyzing Water Pollution in Images from Remote Sensing

M.A. Dias, E. A. Silva, S.C. Azevedo, W. Casaca, T. Statella, R.G. Negri

Remote Sensing

The potential applications of computational tools, such as anomaly detection and incongruence, for analyzing data attract much attention from the scientific research community. However, there remains a need for more studies to determine how anomaly detection and incongruence applied to analyze data of static images from remote sensing will assist in detecting water pollution. In this study, an incongruence-based anomaly detection strategy for analyzing water pollution in images from remote sensing is presented. Our strategy semi-automatically detects occurrences of one type of anomaly based on the divergence between two image classifications (contextual and non-contextual). The results indicate that our strategy accurately analyzes the majority of images. Incongruence as a strategy for detecting anomalies in real-application (non-synthetic) data found in images from remote sensing is relevant for recognizing crude oil close to open water bodies or water pollution caused by the presence of brown mud in large rivers. It can also assist surveillance systems by detecting environmental disasters or performing mappings.

2019

Vessel Optimal Transport for Automated Alignment of Retinal Fundus Images

D. Motta, W. Casaca, A. Paiva

IEEE Transactions on Image Processing

Optimal transport has emerged as a promising and useful tool for supporting modern image processing applications such as medical imaging and scientific visualization. Indeed, the optimal transport theory enables great flexibility in modeling problems related to image registration, as different optimization resources can be successfully used as well as the choice of suitable matching models to align the images. In this paper, we introduce an automated framework for fundus image registration which unifies optimal transport theory, image processing tools and graph matching schemes into a functional and concise methodology. Given two ocular fundus images, we construct representative graphs which embed in their structures spatial and topological information from the eye’s blood vessels. The graphs produced are then used as input by our optimal transport model in order to establish a correspondence between their sets of nodes. Finally, geometric transformations are performed between the images so as to accomplish the registration task properly. Our formulation relies on the solid mathematical foundation of optimal transport as a constrained optimization problem, being also robust when dealing with outliers created during the match- ing stage. We demonstrate the accuracy and effectiveness of the present framework throughout a comprehensive set of qualitative and quantitative comparisons against several influential state-of- the-art methods on various fundus image databases.

Shadow Detection using Object Area-based and Morphological Filtering for Very High-Resolution Satellite Imagery of Urban Areas

S. Azevedo, E. Silva, M. Colnago, R. Negri, W. Casaca

Journal of Applied Remote Sensing

The presence of shadows in remote sensing images leads to misinterpretation of objects and a wrong discrimination of the targets of interest, therefore, limiting the use of several imaging applications. An automatic area-based approach for shadow detection is proposed, which combines spatial and spectral features into a unified and flexible approach. Potential shadow-pixels candidates are identified using morphological-based operators, in particular, black-top-hat transformations as well as area injunction strategies as computed by the well-established normalized saturation-value difference index. The obtained output is a shadow mask, refined in the last step of our method in order to reduce misclassified pixels. Experiments over a large dataset formed by more than 200 scenes of very high-resolution images covering the metropolitan urban area of São Paulo city are performed, where the images are collected from the WorldView-2 (WV-2) and Pléiades-1B (PL-1B) sensors. As verified by an extensive battery of tests, the proposed method provides a good level of discrimination between shadow and nonshadow pixels, with an overall accuracy up to 94.2%, for WV-2, and 90.84%, for PL-1B. Comparative results also attested that the designed approach is very competitive against representative state-of-the-art methods and it can be used for further shadow removal-dependent applications.

2018

Inducing Contextual Classification with Kernel Functions into Support Vector Machines

R. Negri, E.A. Silva, W. Casaca

IEEE Geoscience and Remote Sensing Letters

Kernnel functions have revolutionized theory and practice in the field of pattern recognition, especially to perform image classification. Besides giving rise to nonlinear variants of the well-known support vector machine (SVM), these functions have also been successfully used to classify nonvectorial data (e.g., graphs and collection of sets), in which customized metrics are created to precisely measure the similarity among such contextual data entities. This letter introduces two context-inspired kernel functions as new SVM-driven methods for remote sensing image classification. In contrast to the existing SVM-based approaches that assume only multiattribute vectors as representative features in a high-dimensional space, the proposed models formally establish comparisons between the entire sets of context-given data, thus employing these contextual measurements to drive the classification. More precisely, stochastic distances as well as hypothesis tests are conveniently handled and "kernelized" to build our models. A complete battery of experiments involving both remote sensing and real-world images is conducted to validate the performance of the proposed kernels against various well-established SVM-based methods.

A User-Friendly Interactive Framework for Unsteady Fluid Flow Segmentation and Visualization

D. Motta, W. Casaca, P. Pagliosa, A. Paiva

Journal of Visualization (Visualization Society of Japan)

While vector fields are essential to simulate a large amount of natural phenomena, the difficulty to identify patterns and predict behaviors makes the visual segmentation in simulations an attractive and powerful tool. In this paper, we present a novel user-steered segmentation framework to cope with steady as well as unsteady vector fields on fluid flow simulations. Given a discrete vector field, our approach extracts multi-valued features from the field by exploiting its streamline structures so that these features are mapped to a visual space through a multidimensional projection technique. From an easy-to-handle interface, the user can interact with the projected data so as to partition and explore the most relevant vector features in a guidance frame of the simulation. Besides navigating and visually mining structures of interest, the interactivity with the projected data also allows the user to progressively enhance the segmentation result according to his insights. Finally, to successfully deal with unsteady simulations, the segments previously annotated by the user are used as a training set for a Support Vector Machine approach that classifies the remaining frames in the flow. We attest the effectiveness and versatility of our methodology throughout a set of classical physical-inspired applications on fluid flow simulations as depicted in the experiment results section.

Fundus Image Transformation Revisited: Towards Determining More Accurate Registrations

D. Motta, W. Casaca, A. Paiva

IEEE International Symposium on Computer-Based Medical Systems (CBMS)

Image registration is an important pre-processing step in several computer vision applications, being crucial in medical imaging systems where patients are examined and diagnosed almost exclusively by images. For fundus images, in which microscopic differences are significant to better support medical decisions, an accurate registration is im- perative. Historically, geometric transformations derived from quadratic models have been widely used as a benchmark to perform registration on fundus images, but in this paper, we demonstrate that quadratic and other high-order mappings are not necessarily the best choices for this purpose, even for well-established state-of-the-art registration methods. From a novel overlapping metric designed to determine the best image transformation that maximizes the registration accuracy, we improve the assertiveness of several methods of the literature while still preserving the same computational burden initially reached by those methods.

2017

Shadows Removal in High Resolution Remote Sensing Images using Local Inpainting Strategy

S.C. Azevedo, G.P. Cardim, W. Casaca, E. Silva, R. Singh

20th PECORA - Science for Decisions: Monitoring and Projection (USGS & NASA)

Best paper awards in Remote Sensing (3rd place)

The presence of shadows in Remote Sensing images leads to misinterpretation of objects in several real-world applications, which includes Very High Resolution (VHR) image data from urban areas. Consequently, new methodologies are required to analyze urban data efficiently, due to the great variety of artifacts and shadows formed by elevated objects in the image. In this paper, a novel automatic shadow removal approach is proposed to recover missing information caused by shadows and other obstruction artifacts. First, an automated shadow detection method is applied by computing morphological operations between objects and their surroundings, which are combined with shadow spectral features extracted from a color space model, avoiding, this way, false detections in the shadow-originated mask. Second, to recovering the missing information from the shadow guidance mask, an inpainting-inspired strategy is proposed, which unifies anisotropic diffusion, transport equation and texture synthesis into a robust and concise framework. The performance of our approach is evaluated by taking a WorldView-2 imagery, where it was found that the method achieves an overall accuracy on shadow detection up to 90%, in addition to a low rate of false detection (~20%). Moreover, the designed algorithm outperforms existing recovering techniques, providing high computational performance over VHR satellite images that could be suitable for object recognition, land-cover mapping, 3D reconstruction and, particularly, for developing countries where land use and land cover are rapidly changing with tall buildings/structures within urban areas.

Region-Based Classification of PolSAR Data Through Kernel Methods and Stochastic Distances

R.G. Negri, W. Casaca, E. Silva

Iberoamerican Congress on Pattern Recognition (CIARP)

Stochastic distances combined with Minimum Distance method for region-based classification of Polarimetric Synthetic Aperture Radar (PolSAR) image was successfully verified in Silva et al. (2013). Methods like K-Nearest Neighbors may also adopt stochastic distances and then used in a similar purpose. The present study investigates the use of kernel methods for PolSAR region-based classification. For this purpose, the Jeffries-Matusita stochastic distance between Complex Multivariate Wishart distributions is integrated in a kernel function and then used in Support Vector Machine and Graph-Based kernel methods. A case study regarding PolSAR remote sensing image classification is carried to assess the above mentioned methods. The results show superiority of kernel methods in comparison to the other analyzed methods.

2016

Dealing with Multiple Requirements in Geometric Arrangements

E. Gomez-Nieto, W. Casaca, D. Motta, I. Hartmann, G. Taubin, L.G. Nonato

IEEE Transactions on Visualization and Computer Graphics

Existing algorithms for building layouts from geometric primitives are typically designed to cope with requirements such as orthogonal alignment, overlap removal, optimal area usage, hierarchical organization, among others. However, most techniques are able to tackle just a few of those requirements simultaneously, impairing their use and flexibility. In this work we propose a novel methodology for building layouts from geometric primitives that concurrently addresses a wider range of requirements. Relying on multidimensional projection and mixed integer optimization, our approach arranges geometric objects in the visual space so as to generate well structured layouts that preserve the semantic relation among objects while still making an efficient use of display area. Moreover, scalability is handled through a hierarchical representation scheme combined with navigation tools. A comprehensive set of quantitative comparisons against existing geometry-based layouts and applications on text, image, and video data set visualization prove the effectiveness of our approach.

2015

A User-friendly Interactive Inpainting Framework via Laplacian Coordinates

W. Casaca, D. Motta, G. Taubin, L.G. Nonato

IEEE International Conference on Image Processing (ICIP)

Image inpainting is a challenging topic in computer vision that seeks to recover the natural aspect of an image where data has been partially damaged or occluded by undesired objects. A common drawback not addressed by most inpainting methodologies is that the user must manually provide the inpainting mask as input data to the method. Selecting the inpainting mask is tedious, time consuming and it often requires artistic skills to precisely determine the mask. In this work we design a new tool that allows users to easily select the desirable mask. The proposed framework combines the high-adherence on image contours of the Laplacian Coordinates segmentation approach with the efficiency of a recent inpainting technique that unifies anisotropic diffusion, inner product-based filling order mechanism and exemplar-based completion. The user can interact with the object that he/she intends to edit by stroking small parts of the object so as to proceed with the segmentation and inpainting task. Our comparisons show that the proposed framework has good performance in terms of applicability and effectiveness when compared against other existing techniques in the literature.

Understanding Large Legal Datasets through Visual Analytics

E. Gomez-Nieto, W. Casaca, I. Hartman, L.G. Nonato

28th Conference on Graphics, Patterns and Images (SIBGRAPI)

Databases containing more than one million of legal documents, each with dozens of variables, pose special issues as to the detection of patterns of interest for judges and prosecutors. Most state-of-the-art methods rely on automatic schemes to classify/group data according to their similarity in the hope of uncover useful information, neglecting the knowledge and skill of specialists in the information extraction process. In this work we propose an visual analytics tool made up of a set of linked-views to explore 25 years of data from the Brazilian Supreme Court, all with the purpose of extracting information that traditional methods could not reveal.

Interactive Image Colorization using Laplacian Coordinates

W. Casaca, M. Colnago, L.G. Nonato

Computer Analysis of Images and Patterns (CAIP)

Image colorization is a modern topic in computer vision which aims at manually adding colors to grayscale images. Techniques devoted to colorize images di.ffer in many fundamental aspects as they often require an excessive number of image scribbles to reach pleasant colorizations. In fact, spreading lots of scribbles in the whole image consists of a laborious task that demands great eff.orts from users to accurately set appropriate colors to the image. In this work we present a new framework that only requires a small amount of image annotations to perform the colorization. The proposed framework combines the high-adherence on image contours of the Laplacian Coordinates segmentation approach with a fast color matching scheme to propagate colors to image partitions. User can locally manipulate colored regions so as to further improve the segmentation and thus the colorization result. We attest the .effectiveness of our approach through a set of practical applications and comparisons against existing colorization techniques.

2014

Laplacian Coordinates for Seeded Image Segmentation

W. Casaca, L.G. Nonato, G. Taubin

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Top 5 ranked journal/conference publication according to Google Scholar

Seed-based image segmentation methods have gained much attention lately, mainly due to their good performance in segmenting complex images with little user interaction. Such popularity leveraged the development of many new variations of seed-based image segmentation, which vary greatly regarding mathematical formulation and complexity. Most existing methods in fact rely on complex mathematical formulations that typically do not guarantee unique solution for the segmentation problem while still being prone to be trapped in local minima. In this work we present a novel framework for seed-based image segmentation that is mathematically simple, easy to implement, and guaranteed to produce a unique solution. Moreover, the formulation holds an anisotropic behavior, that is, pixels sharing similar attributes are kept closer to each other while big jumps are naturally imposed on the boundary between image regions, thus ensuring better fitting on object boundaries. We show that the proposed framework outperform state-of-the-art techniques in terms of quantitative quality metrics as well as qualitative visual results.

Similarity Preserving Snippet-Based Visualization of Web Search Results

E. Gomez-Nieto, F. Roman, P. Pagliosa, W. Casaca, E. Helou, M. Oliveira, L.G. Nonato

IEEE Transactions on Visualization and Computer Graphics

Internet users are very familiar with the results of a search query displayed as a ranked list of snippets. Each textual snippet shows a content summary of the referred document (or webpage) and a link to it. This display has many advantages, for example, it affords easy navigation and is straightforward to interpret. Nonetheless, any user of search engines could possibly report some experience of disappointment with this metaphor. Indeed, it has limitations in particular situations, as it fails to provide an overview of the document collection retrieved. Moreover, depending on the nature of the query for example, it may be too general, or ambiguous, or ill expressed the desired information may be poorly ranked, or results may contemplate varied topics. Several search tasks would be easier if users were shown an overview of the returned documents, organized so as to reflect how related they are, content wise. We propose a visualization technique to display the results of web queries aimed at overcoming such limitations. It combines the neighborhood preservation capability of multidimensional projections with the familiar snippet-based representation by employing a multidimensional projection to derive two-dimensional layouts of the query search results that preserve text similarity relations, or neighborhoods. Similarity is computed by applying the cosine similarity over a "bag-of-wordsâ' vector representation of collection built from the snippets. If the snippets are displayed directly according to the derived layout, they will overlap considerably, producing a poor visualization. We overcome this problem by defining an energy functional that considers both the overlapping among snippets and the preservation of the neighborhood structure as given in the projected layout. Minimizing this energy functional provides a neighborhood preserving two-dimensional arrangement of the textual snippets with minimum overlap. The resulting visualization conveys both a global view of the query results and visual groupings that reflect related results, as illustrated in several examples shown.

Combining Anisotropic Diffuison, Transport Equation and Texture Synthesis for Inpainting Textured Images

W. Casaca, M.P. Almeida, M. Boaventura, L.G. Nonato

Pattern Recognition Letters

In this work we propose a new image inpainting technique that combines texture synthesis, anisotropic diffusion, transport equation and a new sampling mechanism designed to alleviate the computational burden of the inpainting process. Given an image to be inpainted, anisotropic diffusion is initially applied to generate a cartoon image. A block-based inpainting approach is then applied so that to combine the cartoon image and a measure based on transport equation that dictates the priority on which pixels are filled. A sampling region is then defined dynamically so as to hold the propagation of the edges towards image structures while avoiding unnecessary searches during the completion process. Finally, a cartoon-based metric is computed to measure likeness between target and candidate blocks. Experimental results and comparisons against existing techniques attest the good performance and flexibility of our technique when dealing with real and synthetic images.

2013

Mixed Integer Optimization for Layout Arrangement

E. Gomez-Nieto, W. Casaca, L.G. Nonato, G. Taubin

26th Conference on Graphics, Patterns and Image (SIBGRAPI)

Best paper award in Graphics and Visualization

Arranging geometric entities in a two-dimensional layout is a common task for most information visualization applications, where existing algorithms typically rely on heuristics to position shapes such as boxes or discs in a visual space. Geometric entities are used as a visual resource to convey information contained in data such as textual documents or videos and th challenge is to place objects with similar content close to each other while still avoiding overlap. In this work we present a novel mechanism to arrange rectangular boxes in a two-dimensional layout which copes with the two properties above, that is, it keeps similar object close and prevents overlap. In contrast to heuristic techniques, our approach relies on mixed integer quadratic programming, resulting in well structured arrangements which can easily be tuned to take different forms. We show the effectiveness of our methodology through a comprehensive set of comparisons against state-of-art methods. Moreover, we employ the proposed technique in video data visualization, attesting its usefulness in a practical application.

Spectral Image Segmentation using Image Decomposition and Inner product-based Metric

W. Casaca, A. Paiva, E. Gomez-Nieto, P. Joia, L.G. Nonato

Journal of Mathematical Imaging and Vision

Image segmentation is an indispensable tool in computer vision applications, such as recognition, detection and tracking. In this work, we introduce a novel user-assisted image segmentation technique which combines image decomposition, inner product-based similarity metric, and spectral graph theory into a concise and unified framework. First, we perform an image decomposition to split the image into texture and cartoon components. Then, an affinity graph is generated and the weights are assigned to its edges according to a gradient-based inner-product function. From the eigenstructure of the affinity graph, the image is partitioned through the spectral cut of the underlying graph. The computational effort of our framework is alleviated by an image coarsening process, which reduces the graph size considerably. Moreover, the image partitioning can be improved by interactively changing the graph weights by sketching. Finally, a coarse-to-fine interpolation is applied in order to assemble the partition back onto the original image. The efficiency of the proposed methodology is attested by comparisons with state-of-art spectral segmentation methods through a qualitative and quantitative analysis of the results.

Denoising Textured Images via Regularized Anisotropic Diffusion

W. Casaca, M.P. Almeida, M. Boaventura

An Introductory Guide to Image and Video Processing (Book Chapter)

In this chapter we present a new feature-preserving image denoising approach that aims restoring noisy images with textures.The proposed method combines regularized anisotropic diffusion and recent harmonic analysis techniques into a unified partial differential equation. The diffusion process is driven by using a wave atom shrinkage combined to gradient-based edge detection, which smooths free-texture regions and penalizes other ones. Two forcing terms are used in order to improve the damaged patterns and hold the essential structures of the image. The selecting of optimal set of parameters is mitigated by a robust genetic algorithm, which enables a good trade-off between automation and user interference. Both theoretical and numerical analysis regard to our equation and the corresponding scale-space are exploited and discussed in detail in this work. The suitable performance of the proposed approach is attested by comparisons against recent texture-sensibility denoising techniques.

2012

Class-specific Metrics for Multidimensional Data Projection applied to CBIR

P.Joia, E. Gomez-Nieto, J.Neto, W. Casaca, G. Botelho, A. Paiva, LG. Nonato

The Visual Computer

Content-based image retrieval is still a challenging issue due to the inherent complexity of images and choice of the most discriminant descriptors. Recent development in the field have introduced multidimensional projections to burst accuracy in the retrieval process, but many issues such as introduction of pattern recognition tasks and deeper user intervention to assist the process of choosing the most discriminant features still remain unaddressed. In this paper we present a novel framework to CBIR that combines pattern recognition tasks, class-specific metrics and multidimensional projection to devise an effective and interactive image retrieval system. User interaction plays an essential role in the computation of the final multidimensional projection from which image retrieval will be attained. Results have shown that the proposed approach outperforms existing methods, turning out to be a very attractive alternativefor managing image data sets

Colorization by Multidimensional Projection

W. Casaca, E. Gomez-Nieto, C.O.L. Ferreira, G. Tavares, P. Pagliosa, F. Paulovich, L.G. Nonato, A. Paiva

25th Conference on Graphics, Patterns and Image (SIBGRAPI)

Most image colorization techniques assign colors to grayscale images by embedding image pixels into a highdimensional feature space and applying a color pattern to each cluster of high-dimensional data. A main drawback of such approach is that, depending on texture patterns and image complexity, clusters of similar pixels can hardly be deﬁned automatically, rendering existing methods prone to fail. In this work we present a novel approach to colorize grayscale images that allows for user intervention. Our methodology makes use of projection to map high-dimensional data to a visual space. User can manipulate projected data in the visual space so as to further improve clusters and thus the colorization result. Different from other methods, our interactive tool is easy of use while still being ﬂexible enough to enable local color modiﬁcation. We show the effectiveness of our approach through a set of examples and comparisons against existing methods.

2011

Spectral Segmentation using Cartoon-Texture Decomposition and Inner Product-based Metric

W. Casaca, A. Paiva, L.G. Nonato

24th Conference on Graphics, Patterns and Image (SIBGRAPI)

Best paper award in Patterns, Images and Computer Vision

This paper presents a user-assisted image partition technique that combines Cartoon-Txture Decomposition, inner product-based similarity metric, and spectral cut into a unified framework. The CTD is used to first split the image into textured and texture-free components, the latter being used to define a gradient-based inner-product function. An affinity graph is then derived and weights are assigned to its edges according to the inner product-based metric. Spectral cut is computed on the affinity graph so as to partition the image. The computational burden of the spectral cut is mitigated by a fine-to-coarse image representation process, which enables moderate size graphs that can be handled more efficiently. The partitioning can be steered by interactively by changing the weights of the graph through user strokes. Weights are updated by combining the texture component computed in the first stage of our pipeline and a recent harmonic analysis technique that captures waving patterns. Finally, a coarse-to-fine interpolation is applied in order to project the partition back onto the original image. The suitable performance of the proposed methodology is attested by comparisons against state-of-art spectral segmentation methods.

2010

A Decomposition and Noise Removal Method combining Diffusion Equation and Wave Atoms for Textured Images

W. Casaca, M. Boaventura

Mathematical Problems in Engineering

We propose a new method that is aimed at denoising images having textures. The method combines a balanced nonlinear partial differential equation driven by optimal parameters, mathematical morphology operators, weighting techniques, and some recent works in harmonic analysis. Furthermore, the new scheme decomposes the observed image into three components that are well defined as structure/cartoon, texture, and noise-background. Experimental results are provided to show the improved performance of our method for the texture-preserving denoising problem.

2009

A Regularized Nonlinear Diffusion Approach for Texture Image Denoising

W. Casaca, M. Boaventura

22th Conference on Graphics, Patterns and Image (SIBGRAPI)

In this paper a new partial differential equation based method is presented for denoising images having textures. The proposed model combines a nonlinear anisotropic diffusion ﬁlter with recent harmonic analysis techniques. A wave atom shrinkage combined to edge detector based on gradient 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.

PhD Thesis and Master Dissertation

PhD Thesis: Graph Laplacian for Spectral Clustering and Seeded Image Segmentation

Wallace Casaca (advisors: Luis Gustavo Nonato & Gabriel Taubin)

Doctoral Thesis, ICMC-USP and Brown University, 161 pages (Published in 2015)

M.Sc. Dissertation (in Portuguese): Restoration of textured images using image decomposition-based approaches and partial differential equations

Wallace Casaca (advisor: Maurílio Boaventura)

M.Sc., Dissertation, IBILCE-UNESP, 191 pages (Published in 20150)