Morphological Convolutional Neural Network Architecture for Digit Recognition

• Published in: IEEE transaction on neural networks and learning systems Vol. 30; no. 9; pp. 2876 - 2885
• Main Authors: Mellouli, Dorra, Hamdani, Tarek M., Sanchez-Medina, Javier J., Ben Ayed, Mounir, Alimi, Adel M.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Benchmarks; Computer architecture; Convolution; Convolutional neural network (CNN); deep neural networks (DNNs); Feature maps; Image recognition; interpretability; morphological CNN (Morph-CNN); Morphological operations; morphological operators; Morphology; Neural networks; Neurons; Pattern recognition; Task analysis
• ISSN: 2162-237X; 2162-2388
• DOI: 10.1109/TNNLS.2018.2890334

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.