CV Lattes
ResearcherID
ORCID
Google Scholar Citations
Universidade de São Paulo (USP). Instituto de Matemática e Estatística (IME) (Institutional affiliation from the last research proposal) Birthplace: Brazil
holds a BSc., MSc and PhD degrees in Computer Science from Universidade de São Paulo (1989, 1996, 2000, respectively). She has joined de Department of Computer Science of IME/USP in 2001, where she is currently an associate professor. Her main research interests include pattern recognition, machine learning, image processing and analyis, specially the application of machine learning technique in image analysis. (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) |
Computer Vision methods are used to extract information from images and videos, but their contextual elements are not always sufficient to extract correct and accurate information. In these cases, content from other sources and types of data such as audio and text, or other information external to the data, such as a priori knowledge, can be used to complement and enrich the context of th…
Scientific research is generating an increasing number of digital images, from micrographs of cells to pictures of galaxies. Automated instruments can capture many images, which are then processed automatically to extract data from them. For this data to be useful to the scientific community and benefit the general public, it needs to be fast to generate (even for millions of images), con…
A central goal in the field of Computer Vision is image understanding. In general, appearance cues are used to detect components of interest and then spatial and hierarchical relations among these components are used to "describe" the image content at the semantic level of interest. Current deep models have reached a stage of evolution in which they are able to learn and transfer low leve…
(Only some records are available in English at this moment)
Convolutional neural networks (CNNs) are widely used in computer vision for different important tasks in image analysis. In scenarios with limited training data, some studies in the literature show that integrating features extracted from images by manually designed algorithms into CNNs can help improve performance. In this project, we are interested in better understanding this fact. In …
Optical telescopes capture images of large areas of the sky in multiple bands. From these signals, the aim is to recognize what each of the observed objects is. Initial approaches used measurements extracted by traditional image and signal processing methods to perform the classification. More modern approaches use neural networks and process the images directly. Due to the number of obje…
Certain anomalies in retinal images are crucial for detecting eye diseases. Among these diseases, one that is relatively common is Diabetic Retinopathy, resulting from the impairment of microvasculature due to Diabetes Mellitus. Early detection of diabetic retinopathy can prevent a significantly prevalent outcome, which is vision loss. In this scientific initiation project, we are interes…
Historically, facial recognition by computers has often been seen as something from science fiction. However, in recent years, methods have been developed that are capable of achieving face recognition with very high success rates, making this technology increasingly present in people's daily lives. This great advance was mainly due to the contributions brought by Deep Learning, the avail…
(Only some records are available in English at this moment)
Ensemble methods have been successfully used to leverage diversity from different models, improving performance, at the cost of inference time. In the situation where the compounding models are neural networks that share the same architecture, merging methods have appeared as an alternative to ensembles, without the drawback of increasing inference time. This research project aims to stud…
Recent deep learning architectures have achieved impressive results on the task of Object Detection. However, such techniques are known to require huge amounts of labeled data in order to properly generalize, which is harder to acquire than traditional image classification data. To improve this situation, the use of image augmentation techniques became standard practice on the literature.…
Image processing is an important step in many image analysis tasks. With deep neural networks, and particularly with the fully convolutional neural networks, one can learn image-to-image transformations from pairs of input-output training images. Although treating individual pixels as independent samples has shown impressive results, there is an understanding that models that take into co…
(Only some records are available in English at this moment)
| 1 / 1 | Ongoing grants |
| 10 / 8 | Completed research grants |
| 3 / 3 | Ongoing scholarships in Brazil |
| 29 / 26 | Completed scholarships in Brazil |
| 4 / 4 | Completed scholarships abroad |
| 47 / 42 | All research grants and scholarships |
| Associated processes | |