Sparse Subspace Clustering Friendly Deep Dictionary Learning for Hyperspectral Image Classification

Subspace clustering techniques have shown promise in hyperspectral image segmentation. The fundamental assumption subspace is that the samples belonging to different clusters/segments lie separable subspaces. What if this condition does not hold? We surmise even hold original space, data may be nonlinearly transformed a space where it will into In work, we propose transformation based on tenets of deep dictionary learning (DDL). particular, incorporate sparse (SSC) loss DDL formulation. Here transforms such representation (of data) show proposed formulation improves over state-of-the-art clustering.