BSS-Based Feature Extraction for Skin Lesion Image Classification

Authors:
Hans Georg Stockmeier;Heidi Bäcker;Wolfgang Bäumler;Elmar W. Lang
Affiliations:
Institute for Biophysics and Physical Biochemistry, University of Regensburg, Germany;Department of Dermatology, Regensburg University Hospital, Germany;Department of Dermatology, Regensburg University Hospital, Germany;Institute for Biophysics and Physical Biochemistry, University of Regensburg, Germany
Venue:
ICA '09 Proceedings of the 8th International Conference on Independent Component Analysis and Signal Separation
Year:
2009

Citing 4
Cited 0

Filtering for Texture Classification: A Comparative Study

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Comparative Study of ICA Filter Structures Learnt from Natural and Urban Images

IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Bio-inspired Applications of Connectionism-Part II
Combining Independent Component Analysis and Self-Organizing Maps for Cell Image Classification

Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
Non-negative Matrix Factorization with Sparseness Constraints

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

We apply filter-based image classification methods to skin lesion images obtained by two different recording systems. The task is to distinguish different malignant and benign diseases. This is done by extracting features form fluorescence images by applying adaptively learnt or predefined filters and applying a standard classification algorithm to the filter outputs. Several methods for filter bank creation such as ICA, PCA, NMF and Gabor filters are compared.