Anselmo Castelo Branco Ferreira

Pós-doutorado

Formação complementar

Idiomas

Áreas de atuação

Participação em eventos

Orientou

Produções bibliográficas

• FERREIRA, ANSELMO ; NOWROOZI, EHSAN ; BARNI, MAURO . VIPPrint: Validating Synthetic Image Detection and Source Linking Methods on a Large Scale Dataset of Printed Documents. JOURNAL OF IMAGING , v. 7, p. 50, 2021.

• CARTA, S. ; FERREIRA, ANSELMO ; FERREIRA, A. C. B. ; RICUPERO, D. R. ; SAIA, R. . Credit Scoring by Leveraging an Ensemble Stochastic Criterion in a Transformed Feature Space. Progress In Artificial Intelligence , v. 1, p. 2192-6360, 2021.

• FERREIRA, ANSELMO ; PURNEKAR, NISCHAY ; BARNI, MAURO . Ensembling Shallow Siamese Neural Network Architectures for Printed Documents Verification in Data-Scarcity Scenarios. IEEE Access , v. 1, p. 1-1, 2021.

• CARTA, S. ; CORRIGA, A. ; FERREIRA, ANSELMO ; FERREIRA, A. C. B. ; PODDA, A. S. ; RICUPERO, D. R. . A multi-layer and multi-ensemble stock trader using deep learning and deep reinforcement learning. APPLIED INTELLIGENCE (DORDRECHT. ONLINE) , v. 1, p. 1, 2020.

• CARTA, S. ; FERREIRA, A. C. B. ; FERREIRA, A. C. B. ; PODDA, A. S. ; RICUPERO, D. R. ; SANNA, A. . Multi-DQN: an Ensemble of Deep Q-Learning Agents for Stock Market Forecasting. EXPERT SYSTEMS WITH APPLICATIONS , v. 164, p. 113820, 2020.

• FERREIRA, ANSELMO ; FELIPUSSI, S. ; PIRES, R. ; AVILA, S. ; SANTOS, G. ; LAMBERT, J. ; HUANG J. ; ROCHA, A. . Eyes in the Skies: A Data-Driven Fusion Approach to Identifying Drug Crops From Remote Sensing Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , v. 1, p. 1-14, 2019.

• CHEN, C. ; MULIN, L. ; FERREIRA, ANSELMO ; FERREIRA, A. C. B. ; HUANG J. ; CAI, R. . A Copy-Proof Scheme based on the Spectral and Spatial Barcoding Channel Models. IEEE Transactions on Information Forensics and Security , p. 1-1, 2019.

• CARTA, S. ; FERREIRA, ANSELMO ; FERREIRA, A. C. B. ; RECUPERO, D. R. ; SAIA, M. ; SAIA, R. . A Combined Entropy-based Approach for a Proactive Credit Scoring. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE , v. 87, p. 103292, 2019.

• CARTA, S. ; CORRIGA, A. ; FERREIRA, ANSELMO ; FERREIRA, A. C. B. ; RECUPERO, D. R. ; SAIA, R. . A Holistic Auto-Configurable Ensemble Machine Learning Strategy for Financial Trading. Computation , v. 7, p. 67, 2019.

• LI, BIN ; WEI, WEIHANG ; FERREIRA, ANSELMO ; FERREIRA, A. C. B. ; TAN, SHUNQUAN . ReST-Net: Diverse Activation Modules and Parallel Sub-nets based CNN for Spatial Image Steganalysis. IEEE SIGNAL PROCESSING LETTERS , v. PP, p. 1-1, 2018.

• FERREIRA, ANSELMO ; GIRALDI, GILSON . Convolutional Neural Network approaches to granite tiles classification. EXPERT SYSTEMS WITH APPLICATIONS , v. 84, p. 1-11, 2017.

• FERREIRA, ANSELMO ; BONDI, LUCA ; BAROFFIO, LUCA ; BESTAGINI, PAOLO ; HUANG, JIWU ; DOS SANTOS, JEFERSSON A. ; TUBARO, STEFANO ; ROCHA, ANDERSON . Data-Driven Feature Characterization Techniques for Laser Printer Attribution. IEEE Transactions on Information Forensics and Security , v. 12, p. 1860-1873, 2017.

• FERREIRA, ANSELMO ; SANTOS, JEFERSSON A. DOS ; ROCHA, A. . Multi-directional and multi-scale perturbation approaches for blind forensic median filtering detection. Intelligent Data Analysis (Print) , v. 20, p. S17-S36, 2016.

• FERREIRA, ANSELMO ; FELIPUSSI, SIOVANI C. ; ALFARO, CARLOS ; FONSECA, PABLO ; VARGAS-MUNOZ, JOHN E. ; DOS SANTOS, JEFERSSON A. ; ROCHA, ANDERSON . Behavior Knowledge Space-Based Fusion for Copy-Move Forgery Detection. IEEE TRANSACTIONS ON IMAGE PROCESSING , v. 25, p. 1-1, 2016.

• FERREIRA, ANSELMO ; NAVARRO, LUIZ C. ; PINHEIRO, GIULIANO ; SANTOS, JEFERSSON A. DOS ; ROCHA, ANDERSON . Laser printer attribution: Exploring new features and beyond. FORENSIC SCIENCE INTERNATIONAL , v. 247, p. 105-125, 2015.

• SILVA, EWERTON ; CARVALHO, TIAGO ; FERREIRA, ANSELMO ; FERREIRA, A. C. B. ; ROCHA, ANDERSON . Going deeper into copy-move forgery detection: exploring image telltales via multi-scale analysis and voting processes. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION , v. 29, p. 16-32, 2015.

• MORAIS, ERIKSON ; FERREIRA, ANSELMO ; FERREIRA, A. C. B. ; CUNHA, SERGIO AUGUSTO ; BARROS, RICARDO M.L. ; ROCHA, ANDERSON ; GOLDENSTEIN, SIOME . A multiple camera methodology for automatic localization and tracking of futsal players. Pattern Recognition Letters , v. 39, p. 21-30, 2014.

• CARTA, S. ; FENU, G. ; FERREIRA, A. C. B. ; FERREIRA, A. C. B. ; RECUPERO, D. R. ; SAIA, R. . A Two-Step Feature Space Transforming Method to Improve Credit Scoring Performance. In: Fred, A.; Salgado, A.; Aveiro, D.; Dietz, J.; Bernardino, J.; Filipe, J.. (Org.). A Two-Step Feature Space Transforming Method to Improve Credit Scoring Performance. 1ed.: Springer, 2021, v. 1297, p. 134-157.

• FERREIRA, A C B ; ROCHA, A. . A Multiscale and Multi-Perturbation Blind Forensic Technique for Median Detecting. In: Bayro-Corrochano; E., Hancock, E. (Org.). A Multiscale and Multi-Perturbation Blind Forensic Technique for Median Detecting. 882ed.: Springer, 2014, v. 8827, p. 302-310.

• FERREIRA, ANSELMO ; BARNI, M. . Attacking and Defending Printer Source Attribution Classifiers in the Physical Domain. In: Multimedia Forensics in the Wild, 2022, Toronto. II Workshop on Multimedia Forensics in the Wild, 2022.

• FERREIRA, ANSELMO ; CHEN, CHANGSHENG ; BARNI, MAURO . Fusing Multiscale Texture and Residual Descriptors for Multilevel 2D Barcode Rebroadcasting Detection. In: 2021 IEEE International Workshop on Information Forensics and Security (WIFS), 2021, Montpellier. 2021 IEEE International Workshop on Information Forensics and Security (WIFS), 2021. p. 1.

• FERREIRA, ANSELMO ; CHEN, HAN ; LI, BIN ; HUANG, JIWU . An Inception-Based Data-Driven Ensemble Approach to Camera Model Identification. In: 2018 IEEE International Workshop on Information Forensics and Security (WIFS), 2018, Hong Kong. 2018 IEEE International Workshop on Information Forensics and Security (WIFS), 2018. p. 1.

• CARVALHO, M. A. G. . A Comparative Study of Image Segmentation by Application of Normalized Cut on Graphs. In: Conference on Graphics, Patterns and Images-Workshop of Thesis and Dissertations, 2012, Ouro Preto. SIBGRAPI Conference on Graphics, Patterns and Images- Workshop of Thesis and Dissertations, 2012.

• MORAIS, ERIKSON ; GOLDENSTEIN, SIOME ; FERREIRA, ANSELMO ; FERREIRA, A. C. B. ; ROCHA, ANDERSON . Automatic Tracking of Indoor Soccer Players Using Videos from Multiple Cameras. In: 2012 XXV SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2012, Ouro Preto. 2012 25th SIBGRAPI Conference on Graphics, Patterns and Images, 2012. p. 174.

• CARVALHO, T. ; COSTA, F. ; SILVA, E. ; ROCHA, A. . Além do óbvio: a análise forense de imagens e a investigação do conteúdo implícito e explícito de fotografias digitais. In: Simpósio Brasileiro de Segurança da Informação e de Sistemas Computacionais, 2012, Curitiba. Simpósio Brasileiro de Segurança da Informação e de Sistemas Computacionais, 2012.

• DE CARVALHO, M A G ; DA COSTA, A L ; FERREIRA, A C B ; FERREIRA, A. C. B. ; MARCONDES CESAR JUNIOR, ROBERTO . Image Segmentation Using Component Tree and Normalized Cut. In: 2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI 2010), 2010, Gramado. 2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images, 2010. v. 0. p. 317.

• CARVALHO, M. A. G. ; COSTA, A. L. . Image Segmentation using Quadtree-Based Similarity Graph and Normalized Cut. In: 15th Iberoamerican congress conference on Progress in pattern recognition, image analysis, computer vision, and applications, 2010, São Paulo. Proceeding CIARP'10 Proceedings of the 15th Iberoamerican congress conference on Progress in pattern recognition, image analysis, computer vision, and applications. Verlag, Berkinxp[õm: Springer, 2010. p. 329-337.

• ROCHA, A. . A Multiscale and Multi-Perturbation Blind Forensic Technique For Median Detecting. In: IX Workshop de Teses, Dissertações e Trabalhos de Iniciação Científica em Andamento do IC-UNICAMP, 2014, Campinas. Anais do IX Workshop de Teses, Dissertações e Trabalhos de Iniciação Científica em Andamento do IC-UNICAMP, 2014.

• CARVALHO, M. A. G. . Um Estudo Comparativo de Segmentação de Imagens por Aplicações do Corte Normalizado em Grafos. In: II Simpósio de Processamento de Sinais da Unicamp, 2011, Campinas. Anais do II Simpósio de Processamento de Sinais da Unicamp, 2011.

• CARVALHO, M. A. G. ; PINTO, T. W. ; CESAR JUNIOR, R. M. . Image Segmentation Using Watershed and Normalized Cut. In: XXII Brazilian Symposium on Computer Graphics and Image Processing, 2009, Rio de Janeiro, RJ. XXII Brazilian Symposium on Computer Graphics and Image Processing, 2009.

• FERREIRA, A. C. B. ; Problemas e Soluções em Análise Forense de Documentos. 2016. (Apresentação de Trabalho/Conferência ou palestra).

• FERREIRA, A. C. B. ; ROCHA, ANDERSON . A Multiscale and Blind Forensic Technique for Median Detecting. 2014. (Apresentação de Trabalho/Congresso).

• FERREIRA, A. C. B. ; Abordagens de Atribuição de Câmera, Impressora e Scanners bem como Detecção de Clonagens em Fotografias DIgitais. 2014. (Apresentação de Trabalho/Comunicação).

• FERREIRA, A. C. B. ; Digital Image Forensics for Devices Attribution. 2014. (Apresentação de Trabalho/Comunicação).

• Análise Forense de Documentos: Estado da Arte e Novos Desafios. 2013. (Apresentação de Trabalho/Conferência ou palestra).

• FERREIRA, A. C. B. ; CARVALHO, M. A. G. . A Comparative Study of Image Segmentation by Application of Normalized Cut on Graphs. 2012. (Apresentação de Trabalho/Congresso).

• FERREIRA, A. C. B. ; CARVALHO, M. A. G. . Um Estudo Comparativo de Segmentação de Imagens por Aplicação do Corte Normalizado em Grafos. 2011. (Apresentação de Trabalho/Simpósio).

• Image Segmentation and Spectral Graph Theory. 2010. (Apresentação de Trabalho/Outra).

• Segmentação de Imagens Utilizando Teoria Espectral de Grafos. 2010. (Apresentação de Trabalho/Outra).

• FERREIRA, A. C. B. ; COSTA, A. L. ; CARVALHO, M. A. G. . Image Segmentation Using Component Tree and Normalized Cuts. 2010. (Apresentação de Trabalho/Conferência ou palestra).

• FERREIRA, A. C. B. ; PINTO, T. W. ; CARVALHO, M. A. G. ; CESAR JUNIOR, R. M. . Image Segmentation Using Watershed and Normalized Cut. 2009. (Apresentação de Trabalho/Simpósio).

• ROCHA, A. ; SILVA, E. ; COSTA, F. ; CARVALHO, T. . Transpondo Fronteiras da Multidisciplinaridade para Lidar Com Falsificações de Imagens e Vídeos no Século XXI. itweb, 2011 (Matéria em mídia generalizada).

Outras produções

Projetos de pesquisa

• 2020 - Atual

  PrintOut - Printed Documents Authentication, Descrição: With the extensive range of document generation devices nowadays, the establishment of computational techniques to find manipulation, detect illegal copies and link documents to their source are useful because (i) finding manipulation can help to detect fake news and manipulated documents; (ii) exposing illegal copies can avoid frauds and copyright violation; and (iii) indicating the owner of an illegal document can provide strong arguments to the prosecution of a suspect. Different machine learning techniques have been proposed in the scientific literature to act in these problems, but many of them are limited as: (i) there is a lack of methodology, which may require different experts to solve different problems; (ii) the limited range of known elements being considered for multi-class classification problems such as source attribution, which do not consider unknown classes in a real-world testing; and (iii) they don?t consider adversarial attacks from an experienced forger. In this research project, we propose to address these problems on two fronts: resilient characterization and classification. In the characterization front, we intend to use multianalysis approaches. Proposed by the candidate in his Ph.D. research, it is a methodology to fuse/ensemble machine learning approaches by considering several investigative scenarios, creating robust classifiers that minimize the risk of attacks. Additionally, we aim at proposing the use of open-set classifiers, which are trained to avoid misclassification of classes not included in the classifier training. We envision solutions to several printed document forensics applications with this setup: source attribution, forgery of documents and illegal copies detection. All the approaches we aim at creating in this project will be done in partnership with a document authentication company, which will provide real-world datasets and new applications.. , Situação: Em andamento; Natureza: Pesquisa. , Integrantes: Anselmo Castelo Branco Ferreira - Coordenador / Mauro Barni - Integrante.

• 2019 - Atual

  Deep features for 2D barcode label anticounterfeiting detection, Descrição: In recent years, the booming development of online merchants has provided new space for the survival of counterfeit and shoddy products, and increased the difficulty of counterfeit and shoddy products. This project intends to use the QR code label to store the anti-counterfeiting features from the surface of the product to verify the authenticity of products from different sales channels. The consumer can photograph the surface of the product to decode the two-dimensional code label and simultaneously extract the anticounterfeiting features of the product, and can judge the authenticity of the product by comparing the label content with the extracted features. This solution can provide new solutions for product anti-counterfeiting problems, reduce the production, verification and rights protection costs of legal parties, and greatly increase the cost of illegally forged goods, thereby safeguarding the national economic interests and people's personal safety.. , Situação: Em andamento; Natureza: Pesquisa. , Alunos envolvidos: Graduação: (1) / Mestrado acadêmico: (1) . , Integrantes: Anselmo Castelo Branco Ferreira - Integrante / Haodong Li - Integrante / Li Mulin - Integrante / Changcheng Chen - Coordenador / CAO SUDAO - Integrante., Financiador(es): Science and Technology Innovation Commission of Shenzhen - Bolsa.

• 2019 - Atual

  DoUtDes: Trasferimento di tecnologie e competenze di Business Intelligence alle aziende dei settori innovativi e tradizionali, Descrição: Il progetto ha l'obiettivo di creare tra le imprese aderenti nuove competenze negli ambiti dello User Profiling, della Semantic Analisys e dei Big Data applicati al web, al mobile, ai social media e all'Internet of Things. Al termine il progetto vedrà la realizzazione e condivisione di una piattaforma tecnologica di business intelligence (denominata DoUtDes) in grado di consentire alle imprese di sviluppare processi aziendali che sfruttino al massimo le opportunità offerte da questo tipo di tecnologie. Il progetto ha anche come obiettivo il trasferimento alle aziende del cluster delle competenze e metodologie connesse allo sfruttamento dei Big Data allo scopo di migliorare la qualità delle azioni di marketing, advertising, ed evoluzione di prodotto.. , Situação: Em andamento; Natureza: Pesquisa. , Integrantes: Anselmo Castelo Branco Ferreira - Integrante / Diego Reforgiato Ricupero - Integrante / Salvatore Carta - Coordenador., Financiador(es): União Sarda - Bolsa.

• 2018 - Atual

  Two-dimensional code anti-counterfeiting labels and key technologies based on deep features, Descrição: In recent years, the vigorous development of online merchants has provided a new opportunity for the survival of counterfeited and shoddy products. This project intends to use the QR-code label to store the anti-counterfeiting features from the surface of the product to verify the authenticity of products from different sales channels. The consumer can photograph the surface of the product to decode the two-dimensional code label and simultaneously extract the anti-counterfeiting features of the product, and can determine the authenticity of the product by comparing the label content with the extracted features. This solution can provide new approaches for product anti-counterfeiting problems and reduce production, verification and rights costs of legitimate parties, and greatly increase the cost of illegally forged goods, thereby safeguarding national economic interests.. , Situação: Em andamento; Natureza: Pesquisa. , Alunos envolvidos: Graduação: (1) / Mestrado acadêmico: (1) . , Integrantes: Anselmo Castelo Branco Ferreira - Integrante / Li Mulin - Integrante / Changsheng Chen - Coordenador / Cai Sudao - Integrante., Financiador(es): Science and Technology Innovation Commission of Shenzhen - Auxílio financeiro.

• 2018 - Atual

  Research on Digital Image Forgery Localization in Complex Situations, Descrição: With the rapid development on image processing technology, tampering images without leaving obvious perceptual artifacts becomes much easier, which would lead to serious negative influences on society, politics, economy, criminal investigation，justice and diplomacy. Digital image forensics is a kind of important technique for identifying the originality and authenticity of digital images. The existing forensic methods, however, are still subjected to many constraints and far away from practical applications, and thus they cannot work well on the tricky problem of locating the tampered regions within an image forgery, especially in some complex situations. For example, the images come from different sources, the tampering methods are diverse, and so on. In order to improve the performance of digital image forgery localization, this project will study forgery localization methods in complex situations. The main research topics are as follows: 1. deep learning based framework for forgery localization; 2. construction of forgery localization features for small regions; 3. design of fusion strategies for forgery localization. This project is supposed to break through the key techniques for image forgery localization in practical situations, and improve the theory and solution of image forgery localization, which will further support the practical applications of image forensic techniques.. , Situação: Em andamento; Natureza: Pesquisa. , Integrantes: Anselmo Castelo Branco Ferreira - Integrante / Haodong Li - Integrante / Jiwu Huang - Coordenador., Financiador(es): Natural National Science Foundation of China - Auxílio financeiro.

• 2017 - 2019

  Multi Analysis and Deep Learning Techniques for Digital Image Forensics and Classification, Descrição: With the extensive range of image acquisition devices and document generation nowadays, the establishment of computational techniques in order to recognize illegal content and assign authorship can be useful in different ways to a forensic scenario: recognizing the content can help identifying crimes in images, and establishing the owner/author can provide strong arguments to the indictment of a suspect. Different techniques have been proposed in the scientific literature to act in these ways, but often many of them fail because: (1) there is a lack of standardization, i.e., different techniques are proposed for different applications, which may require skilled personnel on each application; (2) the laboratory essence of the process, with only a limited range of known elements being considered for classification, not accounting for the unknown nature of the problems during real-world testing and (3) most of techniques proposed so far are proposed based on feature engineering, built based on patterns that it is not guaranteed to happen always. In this research project, we propose to address these problems on two fronts: resilient characterization and classification. For this, we intend to use multi-analysis approaches, in which we explore several scenarios in the investigation together with data-driven characterization by Convolutional Neural Networks. We also aim at proposing the use of Open-Set classifiers in order to generate the classification taking into account the unknown, which is defined as a class not considered in the classifier training. We intend to apply the developed techniques in three image forensic applications: source attribution, digital image forgery detection and natural image forgery detection. At the end of this project, we aim at establishing new standards for Digital Image Forensics taking into account the real nature of this application.. , Situação: Concluído; Natureza: Pesquisa. , Integrantes: Anselmo Castelo Branco Ferreira - Integrante / HUANG, JIWU - Coordenador.

• 2014 - 2019

  DeepEyes: Visual Computing and Machine Intelligence Techniques for Digital Forensics and Electronic Surveillance, Projeto certificado pelo(a) coordenador(a) Anderson de Rezende Rocha em 04/06/2016., Situação: Concluído; Natureza: Pesquisa. , Integrantes: Anselmo Castelo Branco Ferreira - Integrante / Anderson Rocha - Coordenador / Siome Goldenstein - Integrante / SANTOS, JEFERSSON A. DOS - Integrante / Siovani Felipussi - Integrante / William Robson Schwartz - Integrante / Jacques Wainer - Integrante / Edson Borin - Integrante / David Menotti Gomes - Integrante / Arnaldo Albuquerque de Araújo - Integrante / Nelson Luis Saldanha da Fonseca - Integrante / Flavio de Barros Vidal - Integrante / Dibio Leandro Borges - Integrante / Ricardo da Silva Torres - Integrante / André Luiz da Costa Morisson - Integrante / Paulo Max Gil Innocencio Reis - Integrante / Jorge de Albuquerque Lambert - Integrante / Helio Pedrini - Integrante., Financiador(es): Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Auxílio financeiro.

Prêmios