graduate at Electrical Engineering from Federal University of Pernambuco (1988), Master's at Electrical Engineering from University of Campinas (1993) and Ph.d. at Electrical Engineering from University of Campinas (1996). Since 1998 is professor at Institute of Computing, University of Campinas, becoming associate professor in 2003 and full professor in 2011. Has experience in Computer Science, with emphasis on Image Processing, acting in the following topics: Fuzzy object models for recognition and image/video segmentation; interactive image segmentation; design of image operators using graphs; content-based image annotation and retrieval; image analysis and pattern recognition; learning and design of image descriptors; object detection and pose estimation in video; machine learning, classification, and grouping using optimum-path forest; and volumetric visualization. Applications of interest involve Public Health and Parasitology, Plant Biology, Human and Veterinary Medicine, Endodontics, Geology, Biometry, and Agriculture. (Source: Lattes Curriculum)
| News published in Agência FAPESP Newsletter about the researcher |
| More itemsLess items |
| TITULO |
| Articles published in other media outlets ( ): |
| More itemsLess items |
| VEICULO: TITULO (DATA) |
| VEICULO: TITULO (DATA) |
The Data Science Center for Smart Industry acts as an advanced data analytics hub for industry, aiming to improve operational efficiency, product quality, innovation and sustainability through the application of data science and analytics techniques of data in industrial processes. Contact with industries will be mediated by SENAI and operationalized through workshops and thematic meeting…
This proposal is part of a larger research initiative, in which we study a specific class of optimization problems where the objective function is defined as the max-norm, over a set of variables. Such optimization problems have occurred frequently in the image processing literature (e.g., in image filtering, segmentation, and registration problems). It is well known that for many specifi…
In many areas of the Sciences and Engineering, images provide important information about real problems and the assignment by a machine of one or multiple labels per image (annotation) leads to a decision about the problem. However, the machine learning process requires the manual isolation and identification (label assignment) of the content of interest, named sample, in training images.…
Superpixel based research has gained much importance in the field of computer vision over the last decade. Results from algorithms based on superpixels show promise in typical computer vision problems like segmentation, tracking, and, depth estimation. However, generation of superpixels still remains a challenging problem. Many graph-based as well as gradient ascent-based methods are appl…
(Only some records are available in English at this moment)
In recent years, Convolutional Neural Networks (CNNs) have seen immense success in creating models for decision-making and decision-support systems. However, as their complexity increases in attempts to solve harder problems, heavyweight CNNs pose challenges in data requirements, interpretability, and computational resources. Feature Learning from Image Markers (FLIM), a recent methodolog…
Convolutional Neural Networks (CNNs) highly improved image-pattern recognition tasks primarily due to their feature learning function (encoder). However, the absence of designing methodologies under expert control often results in obscure (``opaque-box'') functionality models that are more complex than necessary. This project aims to develop a human-in-the-loop approach to build the encod…
Mesothelioma is an abnormal mass (a tumor) in the layers of tissues surrounding organs of the chest. Malignant Pleural Mesothelioma (MPM) is the most common primary malignancy of the parietal and visceral layers covering the lungs (the pleura). In a healthy individual, such layers of tissues are thinner than a strand of hair. The mesothelioma increases the thickness of the pleura, and it …
Dynamic Trees (DT) is an image segmentation method that grows optimum-path trees (regions) from root pixels (seeds). The seeds compete for the most strongly connected pixels, and the strength of connectedness between seed and pixel is defined during the optimum tree-growing process. DT uses an Image Foresting Transform (IFT) algorithm, which defines each object as an optimum-path forest r…
(Only some records are available in English at this moment)
Cell image segmentation of 3D/4D microscopy images is a complex task due to the lack of signal intensity in some parts of the image, splitting, and merging of cells. Methods based on Deep Learning have been developed to solve the problem automatically, but errors often occur, leading to two subproblems of interest: (1) how can we effectively detect the cells with segmentation errors? (2) …
Mesothelioma is an abnormal mass (a tumor) in the layers of tissues surrounding organs of the chest. Malignant Pleural Mesothelioma (MPM) is the most common primary malignancy of the parietal and visceral layers covering the lungs (the pleura). Current diagnostic pathways depends on invasive methods, such as biopsy. A biomarker from images would be a significant advance to detect the MPM …
Deep neural networks can be very effective for image classification. However, they usually rely on large supervised training sets to reduce/avoid high classification accuracy on the training data with low accuracy on unseen test sets --- a phenomenon known as \emph{data overfitting}. Large supervised (labeled) training sets are usually impractical in applications that require human expert…
(Only some records are available in English at this moment)
| 1 / 1 | Ongoing research grants |
| 11 / 8 | Completed research grants |
| 2 / 2 | Ongoing scholarships in Brazil |
| 42 / 24 | Completed scholarships in Brazil |
| 9 / 8 | Completed scholarships abroad |
| 65 / 43 | All research grants and scholarships |
| Associated processes | |
CV Lattes
ORCID