Pattern recognition in images based on artificial neural networks and complex systems: from handcrafted descriptor extraction to automated learning

• Grant number: 23/04583-2
• Support Opportunities: Regular Research Grants
• Start date: August 01, 2023
• End date: July 31, 2025
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Lucas Correia Ribas
• Grantee: Lucas Correia Ribas
• Host Institution: Instituto de Biociências, Letras e Ciências Exatas (IBILCE). Universidade Estadual Paulista (UNESP). Campus de São José do Rio Preto. São José do Rio Preto , SP, Brazil
• City of the host institution: São José do Rio Preto
• Associated researchers: Antoine Manzanera ; JENNANE Rachid ; Joao Batista Florindo ; Odemir Martinez Bruno

Abstract

Pattern recognition in images is a key topic of computer vision, involving the analysis of visual features (such as texture, color, and shape) and having various applications. Currently, there are two main paradigms of methods, each with advantages and disadvantages: the classic, which uses manual descriptors and requires greater domain knowledge, and approaches based on machine learning with Artificial Neural Networks (ANNs). Classic methods use mathematical or statistical models and are useful in scenarios with limited data, hardware, and a greater need for interpretability. On the other hand, learning-based approaches, such as convolutional neural networks, are gaining popularity due to their ability to learn relevant features from large volumes of data and high classification performance. This project proposes the study and development of methods based on both paradigms, using complex systems techniques and ANNs to develop methods that improve pattern recognition tasks.More specifically, the focus will be on two complex systems approaches: complex networks and deterministic walks. These approaches accurately describe the irregularity or homogeneity of structures in images, relevant for natural and artificial vision, assisting in the analysis of images from nature or stemming from non-linear phenomena.In ANNs, Randomized Neural Networks, Convolutional Neural Networks, and Vision Transformers will be studied, exploring the potential of each architecture in pattern recognition in images and complex systems. Thus, this project can also explore the symbiosis between ANNs and complex systems, investigating and interpreting neural networks from the perspective of complex systems, making the use of these approaches for pattern recognition a natural line of research, as highlighted by some studies. In addition to the theoretical front, as a way to contribute to other areas, another goal is to apply the developed methods to real problem data generated by partners, especially in images of materials (sensors and biosensors), plants, and medical fields. Therefore, it is emphasized that the project seeks to create an interaction between application and theory, testing generic methods in specific problems and, at the same time, allowing these problems to inspire new theoretical lines, advancing knowledge on both fronts. (AU)

Scientific publications

(11)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

FARES, RICARDO T.; RIBAS, LUCAS C.. A New Approach to Learn Spatio-Spectral Texture Representation with Randomized Networks: Application to Brazilian Plant Species Identification. ENGINEERING APPLICATIONS OF NEURAL NETWORKS, EANN 2024, v. 2141, p. 15-pg., 2024-01-01. (23/04583-2, 18/22214-6)

RIBAS, LUCAS C.; BRUNO, ODEMIR M.. Learning a complex network representation for shape classification. PATTERN RECOGNITION, v. 154, p. 10-pg., 2024-05-18. (16/23763-8, 23/04583-2, 21/07289-2, 18/22214-6)

RIBAS, LUCAS C.; SCABINI, LEONARDO F. S.; CONDORI, RAYNER H. M.; BRUNO, ODEMIR M.. Color-texture classification based on spatio-spectral complex network representations. PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, v. 635, p. 15-pg., 2024-01-19. (23/04583-2, 19/07811-0, 21/09163-6, 18/22214-6)

SCABINI, LEONARDO; ZIELINSKI, KALLIL M.; FARES, RICARDO T.; KONUK, EMIR; MIRANDA, GISELE; KOLB, ROSANA M.; RIBAS, LUCAS C.; BRUNO, ODEMIR M.. Deep Texture Feature Aggregation on Leaf Microscopy Images for Brazilian Plant Species Recognition. PROCEEDINGS OF THE 2024 9TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING TECHNOLOGIES, ICMLT 2024, v. N/A, p. 5-pg., 2024-01-01. (23/04583-2, 23/10442-2, 22/03668-1, 24/00530-4, 18/22214-6)

ZIELINSKI, KALLIL M.; SCABINI, LEONARDO; RIBAS, LUCAS C.; DA SILVA, NUBIA R.; BEECKMAN, HANS; VERWAEREN, JAN; BRUNO, ODEMIR M.; DE BAETS, BERNARD. Advanced wood species identification based on multiple anatomical sections and using deep feature transfer and fusion. COMPUTERS AND ELECTRONICS IN AGRICULTURE, v. 231, p. 12-pg., 2025-01-20. (21/09163-6, 23/10442-2, 21/08325-2, 18/22214-6, 22/03668-1, 23/04583-2)

FARES, RICARDO T.; RIBAS, LUCAS C.. Randomized Autoencoder-based Representation for Dynamic Texture Recognition. 2024 31ST INTERNATIONAL CONFERENCE ON SYSTEMS, SIGNALS AND IMAGE PROCESSING, IWSSIP 2024, v. N/A, p. 7-pg., 2024-01-01. (23/04583-2, 18/22214-6)

RIBAS, LUCAS C.; SCABINI, LEONARDO F. S.; SA JUNIOR, JARBAS JOACI DE MESQUITA; BRUNO, ODEMIR M.. Local complex features learned by randomized neural networks for texture analysis. PATTERN ANALYSIS AND APPLICATIONS, v. 27, n. 1, p. 12-pg., 2024-03-01. (23/04583-2, 19/07811-0, 18/22214-6, 21/09163-6, 18/22214-6)

ZIELINSKI, KALLIL M. C.; RIBAS, LUCAS C.; MACHICAO, JEANETH; BRUNO, ODEMIR M.. A network classification method based on density time evolution patterns extracted from network automata. PATTERN RECOGNITION, v. 146, p. 10-pg., 2023-09-29. (23/04583-2, 21/07289-2, 21/08325-2, 20/03514-9, 22/03668-1, 18/22214-6)

ZIELINSKI, KALLIL M. C.; SCABINI, LEONARDO; RIBAS, LUCAS C.; BRUNO, ODEMIR M.. Exploring neighborhood variancy for rule search optimization in Life-like Network Automata. 2024 14TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION SYSTEMS, ICPRS, v. N/A, p. 7-pg., 2024-01-01. (23/04583-2, 23/10442-2, 21/08325-2, 24/00530-4, 18/22214-6)

RIBAS, LUCAS C.; CASACA, WALLACE; FARES, RICARDO T.. Conditional Generative Adversarial Networks and Deep Learning Data Augmentation: A Multi-Perspective Data-Driven Survey Across Multiple Application Fields and Classification Architectures. AI, v. 6, n. 2, p. 24-pg., 2025-02-01. (24/01744-8, 13/07375-0, 23/04583-2, 23/14427-8)

FARES, RICARDO T.; VICENTIM, ANA CATARINA M.; SCABINI, LEONARDO; ZIELINSKI, KALLIL M.; JENNANE, RACHID; BRUNO, ODEMIR M.; RIBAS, LUCAS C.. Randomized Encoding Ensemble: A New Approach for Texture Representation. 2024 31ST INTERNATIONAL CONFERENCE ON SYSTEMS, SIGNALS AND IMAGE PROCESSING, IWSSIP 2024, v. N/A, p. 8-pg., 2024-01-01. (23/04583-2, 22/15840-3, 18/22214-6, 22/03668-1)