A Learning Framework for Morphological Operators using Counter-Harmonic Mean

Abstract : 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.
Type de document :
Communication dans un congrès
Cris L. Luengo Hendriks, Gunilla Borgefors, and Robin Strand. 11th International Symposium, ISMM 2013, May 2013, Uppsala, Sweden. Springer, 7883, pp.329-340, 2013, Lecture Notes in Computer Science. 〈10.1007/978-3-642-38294-9_28〉
Liste complète des métadonnées

https://hal-mines-paristech.archives-ouvertes.fr/hal-00834523
Contributeur : Bibliothèque Mines Paristech <>
Soumis le : dimanche 16 juin 2013 - 07:52:39
Dernière modification le : vendredi 27 octobre 2017 - 17:36:02

Identifiants

Collections

Citation

Jonathan Masci, Jesus Angulo, Jürgen Schmidhuber. A Learning Framework for Morphological Operators using Counter-Harmonic Mean. Cris L. Luengo Hendriks, Gunilla Borgefors, and Robin Strand. 11th International Symposium, ISMM 2013, May 2013, Uppsala, Sweden. Springer, 7883, pp.329-340, 2013, Lecture Notes in Computer Science. 〈10.1007/978-3-642-38294-9_28〉. 〈hal-00834523〉

Partager

Métriques

Consultations de la notice

94