Kenny V. dos Santos
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kenny V. dos Santos has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Bernardo Bentes Gatto
Center for Artificial Intelligence Research (C-AIR), Tsukuba, Japan
2 shared publications - Eulanda Miranda dos Santos
UFAM
2 shared publications - Kazuhiro Fukui
Department of Computer Science, Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan
2 shared publications - Waldir S. S. Junior
Federal University of Amazonas
2 shared publications
Latest Publications
- 30 January 2021
- Published by Springer Nature in Neural Processing Letters
- Vol. 53 (1) , 863
Correction to: Fukunaga–Koontz Convolutional Network with Applications on Character Classification
- 30 January 2021
- Published by Springer Nature in Neural Processing Letters
- Vol. 53 (1) , 863
Correction to: Fukunaga–Koontz Convolutional Network with Applications on Character Classification
- Open Access
- 21 May 2020
- Published by Springer Nature in Neural Processing Letters
- Vol. 52 (1) , 443-465
Fukunaga–Koontz Convolutional Network with Applications on Character Classification
Several convolutional neural network architectures have been proposed for handwritten character recognition. However, most of the conventional architectures demand large scale training data and long training time to obtain satisfactory results. These requirements prevent the use of these methods in a broader range of applications. As an alternative to cope with these problems, we present a new convolutional network for handwritten character recognition based on the Fukunaga–Koontz transform (FKT). Our approach lies in the assumption that Fukunaga–Koontz convolutional kernels can be efficiently learned from subspaces and directly employed to produce high discriminant features in a shallow network architecture. When representing image classes by subspaces, the within-class separability is reduced, since the subspaces form clusters in a low-dimensional space. To increase the between-class separability, we compute a discriminative space from the training subspaces using FKT. By learning convolutional kernels from subspaces, it is possible to extract representative and discriminative features from an image with only a few parameters. Another contribution of the proposed network is the use of pooling layers, which further improves its performance. The proposed method, called Fukunaga–Koontz Network (FKNet), is suitable for solving practical problems, especially when training and processing times are constraints. Four publicly available handwritten character datasets are employed to evaluate the advantages of FKNet. In addition, we demonstrate the flexibility of the proposed method by experiments on LFW dataset.
- 21 May 2020
- Published by Springer Nature in Neural Processing Letters
- Vol. 52 (1) , 443-465
Open AccessFukunaga–Koontz Convolutional Network with Applications on Character Classification
Several convolutional neural network architectures have been proposed for handwritten character recognition. However, most of the conventional architectures demand large scale training data and long training time to obtain satisfactory results. These requirements prevent the use of these methods in a broader range of applications. As an alternative to cope with these problems, we present a new convolutional network for handwritten character recognition based on the Fukunaga–Koontz transform (FKT). Our approach lies in the assumption that Fukunaga–Koontz convolutional kernels can be efficiently learned from subspaces and directly employed to produce high discriminant features in a shallow network architecture. When representing image classes by subspaces, the within-class separability is reduced, since the subspaces form clusters in a low-dimensional space. To increase the between-class separability, we compute a discriminative space from the training subspaces using FKT. By learning convolutional kernels from subspaces, it is possible to extract representative and discriminative features from an image with only a few parameters. Another contribution of the proposed network is the use of pooling layers, which further improves its performance. The proposed method, called Fukunaga–Koontz Network (FKNet), is suitable for solving practical problems, especially when training and processing times are constraints. Four publicly available handwritten character datasets are employed to evaluate the advantages of FKNet. In addition, we demonstrate the flexibility of the proposed method by experiments on LFW dataset.