Random subspace method

Complement (music)

Phenotype

Pattern recognition (psychology)

Subspace topology

Contextual image classification

Politics

Gene

Algorithm

Image (mathematics)

Support vector machine

Hyperspectral imaging

Orthographic projection

Political science

Artificial intelligence

Chemistry

Complementation

Representation (politics)

Computer science

Biochemistry

Projection (relational algebra)

IEEE Transactions on Geoscience and Remote Sensing

Conventional classification algorithms have shown great success for balanced classes. In remote sensing applications, it is often the case that classes are imbalanced. This paper proposes a novel solution to solve the problem of imbalanced training samples in hyperspectral image classification. It consists of two parts: one is for large-size sample sets and the other is for small-size sets. Specifically, an algorithm based on the orthogonal complement subspace projection (OCSP) is proposed to select samples from large-size classes, and an algorithm also based on OCSP is proposed to create artificial samples for small-size ones. The impact on representation-based classifiers, i.e., sparse and collaborative representation classifiers and traditional classifiers (e.g., support vector machine), is investigated. Experimental results demonstrate that the proposed solution can outperform other existing solutions in the literature.

Hyperspectral Image Classification With Imbalanced Data Based on Orthogonal Complement Subspace Projection