A Study on Convolutional Vector-Valued Neural Networks for Color Image Classification

• Carolina Rodrigues UNICAMP
• Marcos Eduardo Valle UNICAMP

DOI: https://doi.org/10.5753/eniac.2025.11952

Resumo

Neural networks have gained significant attention in recent years since the development of deep learning. Vector-valued neural networks (V-nets), including hypercomplex-valued neural networks, are appropriate for processing multidimensional data, such as images or hyperspectral imaging. In this article, we present the mathematical foundation for the development of V-nets. We implement and apply these models for a color image classification task, specifically for detecting acute lymphoblastic leukemia in blood smear images.

Referências

Bayro-Corrochano, E., Vallejo, R., and Arana-Daniel, N. (2005). Geometric preprocessing, geometric feedforward neural networks and Clifford support vector machines for visual learning. Neurocomputing, 67(1-4 SUPPL.):54–105.

Breuils, S., Tachibana, K., and Hitzer, E. (2022). New Applications of Clifford’s Geometric Algebra. Advances in Applied Clifford Algebras 2022 32:2, 32(2):1–39.

Buchholz, S. and Sommer, G. (2001). Clifford Algebra Multilayer Perceptrons. In Geometric Computing with Clifford Algebras, pages 315–334. Springer Berlin Heidelberg.

Buchholz, S. and Sommer, G. (2008). On Clifford neurons and Clifford multi-layer perceptrons. Neural Networks, 21(7):925–935.

Claro, M., Vogado, L., Veras, R., Santana, A., Tavares, J., Santos, J., and MacHado, V. (2020). Convolution Neural Network Models for Acute Leukemia Diagnosis. International Conference on Systems, Signals, and Image Processing, 2020-July:63–68.

Comminiello, D., Grassucci, E., Mandic, D. P., and Uncini, A. (2024). Demystifying the hypercomplex: Inductive biases in hypercomplex deep learning. IEEE Signal Processing Magazine, 41(3):59–71.

Géron, A. (2019). Hands–On Machine Learning with Scikit–Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. O Reilly, Sebastopol, California, USA., 2nd edition.

Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press.

Granero, M. A., Hernández, C. X., and Valle, M. E. (2021). Quaternion-Valued Convolutional Neural Network Applied for Acute Lymphoblastic Leukemia Diagnosis. In Brazilian Conference on Intelligent Systems. BRACIS 2021. Lecture Notes in Computer Science, pages 280–293. Springer, Cham.

Grassucci, E., Mancini, G., Brignone, C., Uncini, A., and Comminiello, D. (2023). Dual quaternion ambisonics array for six-degree-of-freedom acoustic representation. Pattern Recognition Letters, 166:24–30.

Grassucci, E., Zhang, A., and Comminiello, D. (2022). PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions. IEEE Transactions on Neural Networks and Learning Systems, pages 1–13.

Kantor, I. L. and Solodovnikov, A. S. (1989). Hypercomplex Numbers: An Elementary Introduction to Algebras. Springer New York.

Labati, R. D., Piuri, V., and Scotti, F. (2011). All-idb: The acute lymphoblastic leukemia image database for image processing. In 2011 18th IEEE International Conference on Image Processing, pages 2045–2048.

Lecun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521(7553):436–444.

Loan, C. F. (2000). The ubiquitous Kronecker product. Journal of Computational and Applied Mathematics, 123(1-2):85–100.

Muhammad, D., Salman, M., Keles, A., and Bendechache, M. (2025). ALL diagnosis: can efficiency and transparency coexist? An explainble deep learning approach. Scientific Reports, 15(1):1–20.

Parcollet, T., Morchid, M., and Linarès, G. (2020). A survey of quaternion neural networks. Artificial Intelligence Review, 53(4):2957–2982.

Schafer, R. (1961). An Introduction to Nonassociative Algebras. Project Gutenberg.

Valle, M. E. (2024). Understanding vector-valued neural networks and their relationship with real and hypercomplex-valued neural networks: Incorporating intercorrelation between features into neural networks. IEEE Signal Processing Magazine, 41(3):49–58.

Vieira, G. and Valle, M. E. (2022a). A general framework for hypercomplex-valued extreme learning machines. Journal of Computational Mathematics and Data Science, 3:100032.

Vieira, G. and Valle, M. E. (2022b). Acute Lymphoblastic Leukemia Detection Using Hypercomplex-Valued Convolutional Neural Networks. In 2022 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE.

Vogado, L. H., Veras, R. M., Araujo, F. H., Silva, R. R., and Aires, K. R. (2018). Leukemia diagnosis in blood slides using transfer learning in CNNs and SVM for classification. Engineering Applications of Artificial Intelligence, 72:415–422.