Colour cluster analysis for pigment identification

This paper presents image processing algorithms designed to analyse the colour CIE Lab histogram of high resolution images of paintings. Three algorithms are illustrated which attempt to identify colour clusters, cluster shapes due to shading and finally to identify pigments. Using the image collection and pigment list of the National Gallery London large numbers of images within a restricted period have been classified with a variety of algorithms. The image descriptors produced were also used with suitable comparison metrics to obtain content-based retrieval of the images.

[1]  William K. Pratt PIKS Image Processing Software , 2006 .

[2]  David Saunders,et al.  Ten years of art imaging research , 2002, Proc. IEEE.

[3]  Kirk Martinez,et al.  VIPS - a highly tuned image processing software architecture , 2005, IEEE International Conference on Image Processing 2005.

[4]  Paul H. Lewis,et al.  An integrated content and metadata based retrieval system for art , 2004, IEEE Transactions on Image Processing.

[5]  Roy S. Berns,et al.  Pigment Identification of Artist Materials Via Multi-Spectral Imaging , 2001, Color Imaging Conference.