Label Consistent Transform Learning for Hyperspectral Image Classification
This incremental method improves classification accuracy for hyperspectral image analysis, benefiting fields like remote sensing.
The authors tackled hyperspectral image classification by introducing Label Consistent Transform Learning (LCTL), which adds supervision to unsupervised transform learning, resulting in a more than 0.1 improvement in Kappa coefficient compared to state-of-the-art methods.
This work proposes a new image analysis tool called Label Consistent Transform Learning (LCTL). Transform learning is a recent unsupervised representation learning approach; we add supervision by incorporating a label consistency constraint. The proposed technique is especially suited for hyper-spectral image classification problems owing to its ability to learn from fewer samples. We have compared our proposed method on state-of-the-art techniques like label consistent KSVD, Stacked Autoencoder, Deep Belief Network and Convolutional Neural Network. Our method yields considerably better results (more than 0.1 improvement in Kappa coefficient) than all the aforesaid techniques.