A Learning Framework for Morphological Operators Using Counter-Harmonic Mean

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.

[1]  Jürgen Schmidhuber,et al.  Steel defect classification with Max-Pooling Convolutional Neural Networks , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[2]  Sven Behnke,et al.  Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition , 2010, ICANN.

[3]  P. Bullen.  Handbook of means and their inequalities , 1987 .

[4]  Pierre Soille,et al.  Morphological Image Analysis: Principles and Applications , 2003 .

[5]  Luca Maria Gambardella,et al.  Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images , 2012, NIPS.

[6]  Petros Maragos,et al.  MRL-filters: a general class of nonlinear systems and their optimal design for image processing , 1998, IEEE Trans. Image Process..

[7]  Jean Serra,et al.  Image Analysis and Mathematical Morphology , 1983 .

[8]  D. Hubel,et al.  Receptive fields and functional architecture of monkey striate cortex , 1968, The Journal of physiology.

[9]  Jürgen Schmidhuber,et al.  A committee of neural networks for traffic sign classification , 2011, The 2011 International Joint Conference on Neural Networks.

[10]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[11]  Yann LeCun,et al.  Une procedure d'apprentissage pour reseau a seuil asymmetrique (A learning scheme for asymmetric threshold networks) , 1985 .

[12]  Youji Iiguni,et al.  Learning of structuring elements for morphological image model with a sparsity prior , 2010, 2010 IEEE International Conference on Image Processing.

[13]  Philippe Salembier,et al.  Adaptive rank order based filters , 1992, Signal Process..

[14]  Jesús Angulo.  Pseudo-morphological Image Diffusion Using the Counter-Harmonic Paradigm , 2010, ACIVS.

[15]  Joseph F. Murray,et al.  Convolutional Networks Can Learn to Generate Affinity Graphs for Image Segmentation , 2010, Neural Computation.

[16]  Stephen Marshall,et al.  The use of genetic algorithms in morphological filter design , 1996, Signal Process. Image Commun..

[17]  Luca Maria Gambardella,et al.  Convolutional Neural Network Committees for Handwritten Character Classification , 2011, 2011 International Conference on Document Analysis and Recognition.

[18]  Luca Maria Gambardella,et al.  Better Digit Recognition with a Committee of Simple Neural Nets , 2011, 2011 International Conference on Document Analysis and Recognition.

[19]  Philippe Salembier.  Structuring element adaptation for morphological filters , 1992, J. Vis. Commun. Image Represent..

[20]  L. J. van Vliet.  Robust local max-min filters by normalized power-weighted filtering , 2004, ICPR 2004.

[21]  Luca Maria Gambardella,et al.  Flexible, High Performance Convolutional Neural Networks for Image Classification , 2011, IJCAI.