A Robust Color Watershed Transformation and Image Segmentation Defined on RGB Spherical Coordinates

The representation of the RGB color space points in spherical coordinates allows to retain the chromatic components of image pixel colors, pulling apart easily the intensity component. This representation allows the definition of a chromatic distance and a hybrid gradient with good properties of perceptual color constancy. In this chapter, the authors present a watershed based image segmentation method using this hybrid gradient. Oversegmentation is solved by applying a region merging strategy based on the chromatic distance defined on the spherical coordinate representation. The chapter shows the robustness and performance of the approach on well known test images and the Berkeley benchmarking image database and on images taken with a NAO robot.

[1]  Manuel Graña,et al.  A Color Transformation for Robust Detection of Color Landmarks in Robotic Contexts , 2010, PAAMS.

[2]  Katsushi Ikeuchi,et al.  Separating reflection components based on chromaticity and noise analysis , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Lee Slater,et al.  Quantifying tomb geometries in resistivity images using watershed algorithms , 2010 .

[4]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[5]  Ramón Moreno,et al.  Hybrid Color Space Transformation to Visualize Color Constancy , 2010, HAIS.

[6]  Sébastien Lefèvre,et al.  A comparative study on multivariate mathematical morphology , 2007, Pattern Recognit..

[7]  J. Maxwell,et al.  The Scientific Papers of James Clerk Maxwell: Experiments on Colour as perceived by the Eye, with remarks on Colour-Blindness , 2011 .

[8]  David J. Kriegman,et al.  Beyond Lambert: reconstructing specular surfaces using color , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  Javier Toro.  Dichromatic illumination estimation without pre-segmentation , 2008, Pattern Recognit. Lett..

[10]  Joost van de Weijer,et al.  Robust optical flow from photometric invariants , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[11]  Honggang Zhang,et al.  Chromaticity-based separation of reflection components in a single image , 2008, Pattern Recognit..

[12]  Katsushi Ikeuchi,et al.  Illumination chromaticity estimation using inverse-intensity chromaticity space , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[13]  Joachim Weickert,et al.  Illumination-Robust Variational Optical Flow with Photometric Invariants , 2007, DAGM-Symposium.

[14]  Arnold W. M. Smeulders,et al.  Color constancy from physical principles , 2003, Pattern Recognit. Lett..

[15]  Jesús Angulo,et al.  Modelling and segmentation of colour images in polar representations , 2007, Image Vis. Comput..

[16]  Ramón Moreno,et al.  RGB colour gradient following colour constancy preservation , 2010 .

[17]  Issam Dagher,et al.  WaterBalloons: A hybrid watershed Balloon Snake segmentation , 2008, Image Vis. Comput..

[18]  Manuel Graña,et al.  An image color gradient preserving color constancy , 2010, International Conference on Fuzzy Systems.

[19]  Steven A. Shafer,et al.  Using color to separate reflection components , 1985 .

[20]  David J. Kriegman,et al.  Color Subspaces as Photometric Invariants , 2006, CVPR.

[21]  Allan Hanbury,et al.  Mathematical Morphology in the HLS Colour Space , 2001, BMVC.

[22]  Jon Atli Benediktsson,et al.  Segmentation and classification of hyperspectral images using watershed transformation , 2010, Pattern Recognit..