Spatio-Colour Asplünd 's Metric and Logarithmic Image Processing for Colour Images (LIPC)

Guillaume Noyel (1) , Michel Jourlin (1, 2)

1 IPRI - International Prevention Research Institute
2 LHC - Laboratoire Hubert Curien

Asplünd 's metric, which is useful for pattern matching, consists in a double-sided probing, i.e. the over-graph and the sub-graph of a function are probed jointly. This paper extends the Asplünd 's metric we previously defined for colour and multivariate images using a marginal approach (i.e. component by component) to the first spatio-colour Asplünd 's metric based on the vectorial colour LIP model (LIPC). LIPC is a non-linear model with operations between colour images which are consistent with the human visual system. The defined colour metric is insensitive to lighting variations and a variant which is robust to noise is used for colour pattern matching.

Mots clés: Logarithmic Image Processing; Colour image analysis; spatio-colour metric; double-sided probing; Asplünd 's metric; colour Logarithmic Image Processing; colour pattern recognition

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement des images [eess.IV]

Guillaume Noyel, Michel Jourlin. Spatio-Colour Asplünd 's Metric and Logarithmic Image Processing for Colour Images (LIPC). 21st Iberoamerican Congress on Pattern Recognition (CIARP 2016), International Association for Pattern Recognition (IAPR), Nov 2016, Lima, Peru. pp.36-43, ⟨10.1007/978-3-319-52277-7_5⟩. ⟨hal-01316581v3⟩