Extending the Morphological Hit-or-Miss Transform to Deep Neural Networks

While most deep learning architectures are built on convolution, alternative foundations such as morphology are being explored for purposes such as interpretability and its connection to the analysis and processing of geometric structures. The morphological hit-or-miss operation has the advantage th...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2021-11, Vol.32 (11), p.4826-4838
Hauptverfasser:	Islam, Muhammad Aminul, Murray, Bryce, Buck, Andrew, Anderson, Derek T., Scott, Grant J., Popescu, Mihail, Keller, James
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial neural networks Benchmarks Convolution convolutional neural network (CNN) Convolutional neural networks Deep learning Deep Learning - trends Gray-scale hit-or-miss transform Humans Machine learning Morphology Neural networks Neural Networks, Computer Optimization Pattern analysis Pattern Recognition, Automated - methods Pattern Recognition, Automated - trends Target detection Transforms
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!