Self-Balancing Dictionary Learning for Relaxed Collaborative Representation of Hyperspectral Image Classification

Supervised dictionary learning and representation (S-DLR) learning framework has demonstrated its superiority for hyperspectral image classification. Relaxed collaborative representation (RCR) has also been acknowledged as an effective method in balancing the similarity and difference between features. In this article, a new dictionary learning method is introduced to balance the discrimination and reconstruction of training samples. In the dictionary learning stage, two new indicators are designed to measure the discriminability of items and can be improved by optimizing coding coefficients. The imposed $l_{2}$ -norm between the independent item and the mean of class-specific samples constrains the similarity, and the calculated weights measure the difference. In the label determination stage, considering that the residuals of RCR are adversely affected by the significant difference of features, a new classification approach is introduced. Class labels are assigned without calculating the reconstruction errors but calculating the levels of comprehensive contribution from all training samples instead. Since the effectiveness will be degraded when dealing with more complex circumstances, a region-based version is further introduced. It can further improve the discrimination of dictionary items due to the reduced categories in each subimage and reduce the computation cost. The experimental results on several hyperspectral datasets demonstrate that our methods can effectively improve the classification performance.