Title :
Color recognition with a camera: a supervised algorithm for classification
Author :
Lalanne, Tristan ; Lempereur, Christine
Author_Institution :
Office Nat. d´´Etudes et de Recherches Aerospatiales, Centre d´´Etude et de Recherches de Toulouse, France
Abstract :
This paper presents a color recognition algorithm using neuronal techniques, applied to the characterization of thermal paints. The color of such a coating changes with temperature, allowing temperature maps to be established on gas turbine engine components for instance. After a formulation of the classification algorithm, performances are evaluated on a thermal paint samples set. The influence of lighting is studied. The results are compared with those obtained by more classical segmentation algorithms. A temperature profile on a test piece is finally achieved
Keywords :
CCD image sensors; cameras; gas turbines; image classification; image colour analysis; image recognition; learning (artificial intelligence); lighting; neural nets; self-organising feature maps; thermal analysis; CCD color camera; classification algorithm; coating; color recognition algorithm; gas turbine engine components; image classification; lighting; neuronal techniques; segmentation algorithms; self adaptive Kohonen neural network; supervised algorithm; temperature maps; temperature profile; thermal paint samples; thermal paints; Cameras; Character recognition; Classification algorithms; Coatings; Engines; Paints; Performance evaluation; Temperature; Testing; Turbines;
Conference_Titel :
Image Analysis and Interpretation, 1998 IEEE Southwest Symposium on
Conference_Location :
Tucson, AZ
Print_ISBN :
0-7803-4876-1
DOI :
10.1109/IAI.1998.666885
