A Learning Framework for Morphological Operators using Counter-Harmonic Mean - Mines Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

A Learning Framework for Morphological Operators using Counter-Harmonic Mean

Résumé

We present a novel framework for learning morphological operators using counter-harmonic mean. It combines concepts from morphology and convolutional neural networks. A thorough experimental validation analyzes basic morphological operators dilation and erosion, opening and closing, as well as the much more complex top-hat transform, for which we report a real-world application from the steel industry. Using online learning and stochastic gradient descent, our system learns both the structuring element and the composition of operators. It scales well to large datasets and online settings.

Dates et versions

hal-00834523 , version 1 (16-06-2013)

Identifiants

Citer

Jonathan Masci, Jesus Angulo, Jürgen Schmidhuber. A Learning Framework for Morphological Operators using Counter-Harmonic Mean. 11th International Symposium, ISMM 2013, May 2013, Uppsala, Sweden. pp.329-340, ⟨10.1007/978-3-642-38294-9_28⟩. ⟨hal-00834523⟩
142 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More