01780nam 2200361z- 450 991034691330332120231214133417.01000019094(CKB)4920000000101389(oapen)https://directory.doabooks.org/handle/20.500.12854/61858(EXLCZ)99492000000010138920202102d2010 |y 0engurmn|---annantxtrdacontentcrdamediacrrdacarrierVariable illumination and invariant features for detecting and classifying varnish defectsKIT Scientific Publishing20101 electronic resource (158 p. p.)Forschungsberichte aus der Industriellen Informationstechnik / Institut für Industrielle Informationstechnik (IIIT), Karlsruher Institut für Technologie3-86644-537-7 This work presents a method to detect and classify varnish defects on wood surfaces. Since these defects are only partially visible under certain illumination directions, one image doesn't provide enough information for a recognition task. A classification requires inspecting the surface under different illumination directions, which results in image series. The information is distributed along this series and can be extracted by merging the knowledge about the defect shape and light direction.detectionilluminationimage seriesinvariant featuresclassificationPérez Grassi Anaauth1323444BOOK9910346913303321Variable illumination and invariant features for detecting and classifying varnish defects3035563UNINA