Robust hyperspectral image classification with rejection fields

In this paper we present a novel method for robust hyperspectral image classification using context and rejection. Hyper-spectral image classification is generally an ill-posed image problem where pixels may belong to unknown classes, and obtaining representative and complete training sets is costly. Furthermore, the need for high classification accuracies is frequently greater than the need to classify the entire image. We approach this problem with a robust classification method that combines classification with context with classification with rejection. A rejection field that will guide the rejection is derived from the classification with contextual information obtained by using the SegSALSA [1] algorithm. We validate our method in real hyperspectral data and show that the performance gains obtained from the rejection fields are equivalent to an increase the dimension of the training sets.

[1]  Jelena Kovacevic,et al.  Performance measures for classification systems with rejection , 2015, Pattern Recognit..

[2]  Antonio J. Plaza,et al.  Hyperspectral Image Segmentation Using a New Bayesian Approach With Active Learning , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Edgar Arce Santana,et al.  Hidden Markov Measure Field Models for Image Segmentation , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Jelena Kovacevic,et al.  Classification with reject option using contextual information , 2013, 2013 IEEE 10th International Symposium on Biomedical Imaging.

[5]  L MarroquinJose,et al.  Hidden Markov Measure Field Models for Image Segmentation , 2003 .

[6]  Zhihui Wei,et al.  Supervised hyperspectral image classification using sparse logistic regression and spatial-TV regularization , 2013, 2013 IEEE International Geoscience and Remote Sensing Symposium - IGARSS.

[7]  Fabio Roli,et al.  Multi-label classification with a reject option , 2013, Pattern Recognit..

[8]  J. Chanussot,et al.  Hyperspectral Remote Sensing Data Analysis and Future Challenges , 2013, IEEE Geoscience and Remote Sensing Magazine.

[9]  Daniel Cremers,et al.  The Natural Vectorial Total Variation Which Arises from Geometric Measure Theory , 2012, SIAM J. Imaging Sci..

[10]  Jelena Kovacevic,et al.  Alternating direction optimization for image segmentation using hidden Markov measure field models , 2014, Electronic Imaging.

[11]  Jelena Kovacevic,et al.  Supervised hyperspectral image segmentation: A convex formulation using hidden fields , 2014, 2014 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).

[12]  C. K. Chow,et al.  On optimum recognition error and reject tradeoff , 1970, IEEE Trans. Inf. Theory.

[13]  José M. Bioucas-Dias,et al.  An Augmented Lagrangian Approach to the Constrained Optimization Formulation of Imaging Inverse Problems , 2009, IEEE Transactions on Image Processing.