6533b7d7fe1ef96bd1269085

RESEARCH PRODUCT

Hyperspectral detection of citrus damage with Mahalanobis kernel classifier

Gustau Camps-vallsJosé BlascoJ. GómezEnrique Moltó

subject

Mahalanobis distanceContextual image classificationbusiness.industryComputer scienceHyperspectral imagingPattern recognitionObject detectionSupport vector machineKernel (linear algebra)Kernel methodKernel (image processing)Computer visionArtificial intelligenceElectrical and Electronic EngineeringbusinessClassifier (UML)

description

Presented is a full computer vision system for the identification of post-harvest damage in citrus packing houses. The method is based on the combined use of hyperspectral images and the Mahalanobis kernel classifier. More accurate and reliable results compared to other methods are obtained in several scenarios and acquired images.

yearjournalcountryeditionlanguage
2007-01-01
http://hdl.handle.net/20.500.11939/5293