Hyperspectral image spectral-spatial classification via weighted Laplacian smoothing constraint-based sparse representation

Robust sparse smooth principal component analysis for face reconstruction and recognition

Existing Robust Sparse Principal Component Analysis (RSPCA) does not incorporate the two-dimensional spatial structure information of images. To address this issue, we introduce a smooth constraint that characterizes the spatial structure information of images into conventional RSPCA, generating a novel algorithm called Robust Sparse Smooth Principal Component Analysis (RSSPCA). The proposed RSSPCA achieves three key objectives simultaneously: robustness through L1-norm optimization, sparsity for feature selection, and smoothness for preserving spatial relationships. Within the Minorization-Maximization (MM) framework, an iterative process is designed to solve the RSSPCA optimization problem, ensuring that a locally optimal solution is achieved. To evaluate the face reconstruction and recognition performance of the proposed algorithm, we conducted comprehensive experiments on six benchmark face databases. Experimental results demonstrate that incorporating robustness and smoothness improves reconstruction performance, while incorporating sparsity and smoothness improves classification performance. Consequently, the proposed RSSPCA algorithm generally outperforms existing algorithms in face reconstruction and recognition. Additionally, visualization of the generalized eigenfaces provides intuitive insights into how sparse and smooth constraints influence the feature extraction process. The data and source code from this study have been made publicly available on the GitHub repository: https://github.com/yuzhounh/RSSPCA.

A fast hyperspectral change detection algorithm for agricultural crops based on spatial reconstruction

Crop change detection plays a pivotal role in ensuring agricultural sustainability and environmental monitoring. Leveraging the high spectral resolution of hyperspectral imagery and bi-temporal analysis, this study presents a Fast Hyperspectral Change Detection algorithm based on Spatial Reconstruction (FHCDSR) designed to identify subtle agricultural changes with improved accuracy and computational efficiency. The proposed method incorporates three key innovations: (1) boundary-constrained preprocessing of 3D hyperspectral data, (2) Laplacian-regularized spatial reconstruction, and (3) a novel tensor-based change detection framework. We conduct a comprehensive evaluation of FHCDSR using two datasets: the Hermiston dataset and the Yancheng dataset. Experimental results demonstrate that FHCDSR achieves superior performance on both datasets, with AUC values of 90.20% (Hermiston) and 95.39% (Yancheng), outperforming six state-of-the-art comparison methods by 3.39-14.78% in detection accuracy. Remarkably, the algorithm maintains high computational efficiency, completing analyses in 9.76 seconds (Hermiston) and 10.90 seconds (Yancheng), representing up to 94.05% reduction in processing time compared to conventional methods. The consistent performance across different agricultural landscapes highlights FHCDSR's robustness as an unsupervised change detection solution, with significant potential for precision agriculture and wetland ecosystem monitoring applications.