A comparison of autonomous techniques for multispectral image analysis and classification

摘要

Multispectral imaging has given place to important applications related to classification and identification ofobjects from a scene. Because of multispectral instruments can be used to estimate the reflectance of materialsin the scene, these techniques constitute fundamental tools for materials analysis and quality control. Duringthe last years, a variety of algorithms has been developed to work with multispectral data, whose main purposehas been to perform the correct classification of the objects in the scene. The present study introduces abrief review of some classical as well as a novel technique that have been used for such purposes. The use ofprincipal component analysis and iK/i-means clustering techniques as important classification algorithms is herediscussed. Moreover, a recent method based on the imin-W/i and imax-M/i lattice auto-associative memories, thatwas proposed for endmember determination in hyperspectral imagery, is introduced as a classification method.Besides a discussion of their mathematical foundation, we emphasize their main characteristics and the resultsachieved for two exemplar images conformed by objects similar in appearance, but spectrally different. Theclassification results state that the first components computed from principal component analysis can be used tohighlight areas with different spectral characteristics. In addition, the use of lattice auto-associative memoriesprovides good results for materials classification even in the cases where some spectral similarities appears intheir spectral responses.© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.