Representation learning and characterization of complex networks with applications in computer vision

• Lucas Correia Ribas USP
• Odemir Martinez Bruno USP

DOI: https://doi.org/10.5753/ctd.2022.223252

Abstract

This work aims to investigate and propose new modeling and characterization techniques for complex networks focusing on application to computer vision problems. Regarding modeling, an efficient and optimized approach to map texture images and videos into directed complex networks was studied. Regarding the characterization, new ways of characterizing complex networks were investigated, with emphasis on the use of randomized neural networks to representation learning, resulting in several proposed methods for analyzing gray-level, color and dynamic textures and shape analysis. Promising results have been achieved by the developed methods in comparison to literature methods in image classification tasks using several benchmark datasets. Additionally, to assess the potential of the developed methods, five applications were investigated in real problems in the areas of biology, botany, physical-chemistry and medicine, achieving interesting results and contributing to the development of these areas.

Keywords: Pattern Recognition, Complex Networks, Machine Learning, Artificial Neural Networks, Computer Vision

References

Backes, A. R. (2010). Estudos de métodos de análise de complexidade em imagens. Doutorado em Ciências Matemáticas e de Computação, ICMC - Universidade de São Paulo, São Carlos.

Backes, A. R., Casanova, D., and Bruno, O. M. (2009). A complex network-based approach for boundary shape analysis. Pattern Recognition, 42(1):54–67.

Banerjee, A. and Jost, J. (2008). Spectral plot properties: Towards a qualitative classification of networks. NHM, 3(2):395–411.

Costa, L. d. F., Rodrigues, F., Travieso, G., and Boas, P. R. V. (2007). Characterization of complex networks: A survey of measurements. Advances in Physics, 56(1):167–242.

Gama, J., Faceli, K., Lorena, A., and De Carvalho, A. (2011). Inteligência artificial: uma abordagem de aprendizado de máquina. Grupo Gen - LTC.

Gonçalves, W. N., Machado, B. B., and Bruno, O. M. (2015). A complex network approach for dynamic texture recognition. Neurocomputing, 153:211 – 220.

Huang, G.-B., Zhu, Q.-Y., and Siew, C.-K. (2006). Extreme learning machine: theory and applications. Neurocomputing, 70(1):489–501.

Ibau, C., Arshad, M. M., and Gopinath, S. C. (2017). Current advances and future visions on bioelectronic immunosensing for prostate-specific antigen. Biosensors and Bioelectronics, 98:267–284.

Machicao, J., Corrêa, E. A., Miranda, G. H. B., Amancio, D. R., and Bruno, O. M. (2018). Authorship attribution based on life-like network automata. PLOS ONE, 13(3):e0193703.

Miranda, G. H. B., Machicao, J., and Bruno, O. M. (2016). Exploring spatio-temporal dynamics of cellular automata for pattern recognition in networks. Scientific Reports, 6(37329).

Nanni, L., Ghidoni, S., and Brahnam, S. (2017). Handcrafted vs. non-handcrafted features for computer vision classification. Pattern Recognition, 71:158–172.

Pao, Y.-H., Park, G.-H., and Sobajic, D. J. (1994). Learning and generalization characteristics of the random vector functional-link net. Neurocomputing, 6(2):163–180.

Purwins, H., Li, B., Virtanen, T., Schlüter, J., Chang, S.-Y., and Sainath, T. (2019). Deep learning for audio signal processing. IEEE Journal of Selected Topics in Signal Processing, 13(2):206–219.

Ribas, L. C. (2021). Aprendizado de representações e caracterização de redes complexas com aplicações em visão computacional. Doutorado em ciências de computação e matemática computacional, ICMC - Universidade de São Paulo.

Ribas, L. C., de Mesquita Sá Junior, J. J., Manzanera, A., and Bruno, O. M. (2022a). Learning graph representation with randomized neural network for dynamic texture classification. Applied Soft Computing, 114:108035.

Ribas, L. C., Neiva, M. B., and Bruno, O. M. (2019). Distance transform network for shape analysis. Information Sciences, 470:28 – 42.

Ribas, L. C., Riad, R., Jennane, R., and Bruno, O. M. (2022b). A complex network based approach for knee osteoarthritis detection: Data from the osteoarthritis initiative. Biomedical Signal Processing and Control, 71:103133.

Ribas, L. C., Sá Junior, J. J. M., Scabini, L. F., and Bruno, O. M. (2020). Fusion of complex networks and randomized neural networks for texture analysis. Pattern Recognition, 103:107189.

Rodrigues, V. C., Soares, J. C., Soares, A. C., Braz, D. C., Melendez, M. E., Ribas, L. C., Scabini, L. F., Bruno, O. M., Carvalho, A. L., Reis, R. M., et al. (2021). Electrochemical and optical detection and machine learning applied to images of genosensors for diagnosis of prostate cancer with the biomarker pca3. Talanta, 222:121444.

Sá Junior, J. J. M. and Backes, A. R. (2016). ELM based signature for texture classification. Pattern Recognition, 51:395–401.

Sá Junior, J. J. M., Ribas, L. C., and Bruno, O. M. (2019). Randomized neural network based signature for dynamic texture classification. Expert Systems with Applications, 135:194–200.

Scabini, L. F., Fistarol, D. O., Cantero, S. V., Gonçalves, W. N., Machado, B. B., and Rodrigues Jr, J. F. (2017). Angular descriptors of complex networks: A novel approach for boundary shape analysis. Expert Systems with Applications, 89:362–373.

Schmidt, W. F., Kraaijveld, M. A., and Duin, R. P. W. (1992). Feedforward neural networks with random weights. In Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems, pages 1–4.

Simon, P. and Uma, V. (2020). Deep learning based feature extraction for texture classification. Procedia Computer Science, 171:1680–1687.

Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. A. (2017). Inception-v4, inceptionresnet and the impact of residual connections on learning. In Thirty-First AAAI Conference on Artificial Intelligence.

Xin, R., Zhang, J., and Shao, Y. (2018). Complex network classification with convolutional neural network. CoRR, abs/1802.00539.

Young, T., Hazarika, D., Poria, S., and Cambria, E. (2018). Recent trends in deep learieee Computational intelligenCe magazine, ning based natural language processing. 13(3):55–75.