We present a framework for hyperspectral image (HSI) analysis validation, specifically abundance fraction estimation based on HSI measurements of water soluble dye mixtures printed on microarray chips. In our work we focus on the performance of two algorithms, the Least Absolute Shrinkage and Selection Operator (LASSO) and the Spatial LASSO (SPLASSO). The LASSO is a statistical method for simultaneously performing model estimation and variable selection. In the context of estimating abundance fractions in a HSI scene, the sparse representations provided by the LASSO are appropriate as not every pixel will be expected to contain every endmember. The SPLASSO is a novel approach which takes the framework of the LASSO algorithm a step further and incorporates the rich spatial information which is available in HSI to further improve the estimates of abundance. Using the HSI measurements of the dye mixtures as a test bed, we show our algorithms improvement over the standard LASSO.
Citation: Biomedical Optics Express
Pub Type: Journals
Probability theory, stochastic processes, and statistics (000.5490), Multispectral and hyperspectral imaging (110.4234), Instrumentation, measurement, and metrology (120.0120), Medical optics and biotechnology (170.0170), Medical and biological imaging (170.3880), Microscopy (180.0180), Optical standards and testing (350.4800).