Title :
Colour and Multispectral Morphological Processing
Author_Institution :
Lab. A2SI, Univ. Paris-Est, Noisy-le-Grand
Abstract :
The classical colour polar-based representations (HLS, HSV, etc.) lead to brightness and saturation with non consistent properties. The requirements for a correct quantitative colour polar representation are recalled. They lead to using norms, and in particular the L1 norm. Colour images are multivariable functions, and for segmenting them one must go through reducing step. It is classically obtained by calculating a gradient module,which is then segmented as a gray tone image. An alternative solution is proposed in the paper. It is based on separated segmentations, followed by final merging into a unique partition. The generalization of the top-hat transformation for extracting colour details is also considered. These new marginal colour operators take advantage of an adaptive combination of the chromatic and the achromatic (or the spectral and the spatio-geometric) colour components. Examples in feature extraction from geographical maps are given.
Keywords :
feature extraction; geophysical signal processing; image colour analysis; image representation; image segmentation; colour polar-based representations; feature extraction; geographical maps; gradient module; gray tone image; marginal colour operators; multispectral morphological processing; multivariable functions; top-hat transformation; Color; L1 norm; colour details; colour segmentation; jump connection; luminance/saturation/hue; multi-spectral segmentation; top-hat;
Conference_Titel :
Advances in Pattern Recognition, 2009. ICAPR '09. Seventh International Conference on
Conference_Location :
Kolkata
Print_ISBN :
978-1-4244-3335-3
DOI :
10.1109/ICAPR.2009.109