IEEE Trans Neural Netw Learn Syst. 2019 Sep;30(9):2876-2885. doi: 10.1109/TNNLS.2018.2890334. Epub 2019 Jan 23.
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.
深度神经网络在许多应用和领域中已经证明了其良好的效果，但它们仍然被视为一个黑盒。因此，引入可解释性方面的内容来防止盲目应用深度网络是非常有用的。本文提出了一种可解释的形态卷积神经网络，称为 Morph-CNN，用于模式识别，其中使用反调和均值将形态操作合并到卷积层中，以生成增强的特征图。Morph-CNN 在 MNIST 和 SVHN 基准数据集上进行了数字识别的广泛评估。不同的测试配置表明，Morph-CNN 优于现有的方法。
