AMAndrea Britto Mattos

Andrea Britto Mattos

*This is an algorithmically generated author record based on publicly available information.

Andrea Britto Mattos has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Desenvolvimento profissional docente e diretrizes para formação de professores no Brasil: uma reflexão crítica

    by Adenilson Mariotti Mattos, Orlando Fernández Aquino

    Fez-se uma análise da concepção de Desenvolvimento Profissional Docente (DPD) que aparece nas Diretrizes Curriculares Nacionais, para a Formação dos Professores da Educação Básica. O objetivo foi compreender a concepção do DPD presente no contexto das Resoluções CNE/CP n.º 2/2015, CNE/CP n.º 2/2019 e CNE/CP n.º 1/ 2020. A metodologia se fundamenta na epistemologia dialético-materialista e no enfoque qualitativo da investigação educacional. No plano operacional, usaram-se a pesquisa documental e a pesquisa bibliográfica. A primeira, para a exploração das Resoluções estudadas, e a segunda para a extração dos resultados dos artigos tomados como fontes de evidências. Nos resultados, se destaca uma concepção do DPD como uma prática profissional complexa, contraditória e duradoura, já que abarca um antes, um durante e um depois da formação inicial. A discussão permitiu revelar que a partir de 2015, o conceito de DPD e as Diretrizes Curriculares para Formação de Professores no Brasil foram-se deteriorando, numa submissão às políticas neoliberais impostas pelos organismos internacionais. As conclusões ressaltam que é necessário retomar a centralidade do trabalho docente e sua sustentação numa política de DPD vinculada à valorização profissional como estratégia de enfrentamento das políticas neoliberais.

  • Simplifying Horizon Picking Using Single-Class Semantic Segmentation Networks

    by Danilo Calhes, Felipe K. Kobayashi, Andrea Britto Mattos, Maysa M. G. Macedo, Dario A. B Oliveira

    Seismic image processing plays a significant role in geological exploration as it conditions much of the interpretation performance. The interpretation process comprises several tasks, and Horizon Picking is one of the most time-consuming. Thereat, several works proposed methods for picking horizons automatically, mostly focusing on increasing the accuracy of data-driven approaches, by employing, for instance, semantic segmentation networks. However, these works often rely on a training process that requires several annotated samples, which are known to be scarce in the seismic domain, due to the overwhelming effort associated with manually picking several horizons in a seismic cube. This paper aims to evaluate the simplification of the labeling process required for training, by using training samples composed of disconnected horizons tokens, therefore relaxing the requirement of annotating the full set of horizons from each training sample, as commonly observed in previous works employing semantic segmentation networks. We assessed two state-of-art neural networks for general-purpose domains (PSP-Net and Deeplab V3+) using public seismic data (Netherlands F3 Block dataset). Our results report a minor impact in the performance using our proposed incomplete token training scheme compared to the complete one, moreover, we report that these networks outperform the current state-of-art for horizon picking from small training sets. Thus, our approach proves to be advantageous for the interpreter, given that using partial results instead of providing a full annotation can reduce the user effort during the labeling process required for training the models.


  • Experimental Analysis of Citrus Tree Classification from UAV Images

    by Felipe Kawashita Kobayashi, Andrea Britto Mattos, Bruno H. Gemignani, Maysa M. G. Macedo

    Nowadays, agricultural producers are increasingly attempting to combine computer vision methods with the output from unmanned aerial vehicles (UAVs) to automate farm operations aiming at speed, precision, and cost. In this context, time-consuming tasks such as crop monitoring may be solved in a more efficient and less error-prone manner. In particular, for estimating productivity and managing pests, a key task that may be automated is the characterization of crop regions into full-grown trees, tree seedlings, tree gaps, and background. In this paper, we address the classification of aerial images into these classes, targeting at samples from a citrus plantation acquired by UAVs. Although Deep Learning-based approaches have been used successfully for many classification problems, little is discussed on the effects of parameters tuning (involving features, classifiers, and sampling methods) for each specific problem. Therefore, our goal is to solve this task while addressing explainability, by running an experimental analysis that explores classical methods as well as Deep Learning-based approaches.


  • Towards View-Independent Viseme Recognition Based on CNNS and Synthetic Data

    by Andrea Britto Mattos, Dario Augusto Borges Oliveira, Edmilson Da Silva Morais

    Visual Speech Recognition is the ability to interpret spoken text using video information only. To address such task automatically, recent works have employed Deep Learning and obtained high accuracy on the recognition of words and sentences uttered in controlled environments, with limited head-pose variation. However, the accuracy drops for multi-view datasets and when it comes to interpreting isolated mouth shapes, such as visemes, the values reported are considerably lower, as shorter segments of speech lack temporal and contextual information. In this work, we evaluate the applicability of synthetic datasets for assisting recognition of visemes in real-world data acquired under controlled and uncontrolled environments, using GRID and AVICAR datasets, respectively. We create two large-scale synthetic 2D datasets based on realistic 3D facial models - with near-frontal and multi-view mouth images. We perform experiments that indicate that a transfer learning approach using synthetic data can get higher accuracy than training from scratch using real data only, on both scenarios.