Supervised Object Class Colour Normalisation

Colour is an important cue in many applications of computer vision and image processing, but robust usage often requires estimation of the unknown illuminant colour. Usually, to obtain images invariant to the illumination conditions under which they were taken, color normalisation is used. In this work, we develop a such colour normalisation technique, where true colours are not important per se but where examples of same classes have photometrically consistent appearance. This is achieved by supervised estimation of a class specific canonical colour space where the examples have minimal variation in their colours. We demonstrate the effectiveness of our method with qualitative and quantitative examples from the Caltech-101 data set and a real application of 3D pose estimation for robot grasping.

[1]  Henrik Gordon Petersen,et al.  Pose estimation using local structure-specific shape and appearance context , 2013, 2013 IEEE International Conference on Robotics and Automation.

[2]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[3]  Frédéric Jurie,et al.  Learned color constancy from local correspondences , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[4]  Joni-Kristian Kämäräinen,et al.  Learning and Detection of Object Landmarks in Canonical Object Space , 2010, 2010 20th International Conference on Pattern Recognition.

[5]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[6]  Joost van de Weijer,et al.  Computational Color Constancy: Survey and Experiments , 2011, IEEE Transactions on Image Processing.

[7]  Dani Lischinski,et al.  Personalization of image enhancement , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  O. Chum,et al.  On the Interaction between Object Recognition and Colour Constancy , 2003 .

[9]  Cordelia Schmid,et al.  Using High-Level Visual Information for Color Constancy , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[10]  S. Umeyama,et al.  Least-Squares Estimation of Transformation Parameters Between Two Point Patterns , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Olivier Alata,et al.  Is there a best color space for color image characterization or representation based on Multivariate Gaussian Mixture Model? , 2009, Comput. Vis. Image Underst..

[12]  Rüdiger Dillmann,et al.  The KIT object models database: An object model database for object recognition, localization and manipulation in service robotics , 2012, Int. J. Robotics Res..

[13]  Marc Ebner,et al.  Color Constancy , 2007, Computer Vision, A Reference Guide.

[14]  K. Gegenfurtner,et al.  Memory modulates color appearance , 2006, Nature Neuroscience.

[15]  Marc Pollefeys,et al.  Robust Radiometric Calibration and Vignetting Correction , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Steven J. Gortler,et al.  The von Kries Hypothesis and a Basis for Color Constancy , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[17]  Erik Reinhard,et al.  Color Transfer between Images , 2001, IEEE Computer Graphics and Applications.

[18]  D. Foster.  Color constancy , 2011, Vision Research.

[19]  Nathalie Guyader,et al.  When viewing natural scenes, do abnormal colors impact on spatial or temporal parameters of eye movements? , 2012, Journal of vision.