Please use this identifier to cite or link to this item:
http://hdl.handle.net/10553/55092
Title: | Morphological convolutional neural network architecture for digit recognition | Authors: | Mellouli, Dorra Hamdani, Tarek M. Sanchez-Medina, Javier J. Ayed, Mounir Ben Alimi, Adel M. |
UNESCO Clasification: | 120304 Inteligencia artificial | Keywords: | Convolutional neural network (CNN) Deep neural networks (DNNs) Image recognition Interpretability Morphological CNN (Morph-CNN), et al |
Issue Date: | 2019 | Publisher: | 2162-237X | Journal: | IEEE Transactions on Neural Networks and Learning Systems | Abstract: | Deep neural networks have proved promising results in many applications and fields, but they are still assimilated to a black box. Thus, it is very useful to introduce interpretability aspects to prevent the blind application of deep networks. This paper proposed an interpretable morphological convolutional neural network called Morph-CNN for pattern recognition, where morphological operations were incorporated using counter-harmonic mean into the convolutional layer in order to generate enhanced feature maps. Morph-CNN was extensively evaluated on MNIST and SVHN benchmarks for digit recognition. The different tested configurations showed that Morph-CNN outperforms the existing methods. | URI: | http://hdl.handle.net/10553/55092 | ISSN: | 2162-237X | DOI: | 10.1109/TNNLS.2018.2890334 | Source: | IEEE Transactions on Neural Networks and Learning Systems [ISSN 2162-237X], v. 30 (9), p. 2876 - 2885 |
Appears in Collections: | Artículos |
SCOPUSTM
Citations
48
checked on May 28, 2023
WEB OF SCIENCETM
Citations
35
checked on Oct 2, 2022
Page view(s)
148
checked on May 27, 2023
Google ScholarTM
Check
Altmetric
Share
Export metadata
Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.