Exemplar-Based Colour Constancy

Exemplar-based learning or, equally, nearest neighbour methods have recently gained interest from researchers in a variety of computer science domains because of the prevalence of large amounts of accessible data and storage capacity. In computer vision, these types of technique have been successful in several problems such as scene recognition, shape matching, image parsing, character recognition and object detection. Applying the concept of exemplar-based learning to the problem of colour constancy seems odd at first glance since, in the first place, similar nearest neighbour images are not usually affected by precisely similar illuminants and, in the second place, gathering a dataset consisting of all possible real-world images, including indoor and outdoor scenes and for all possible illuminant colours and intensities, is indeed impossible. In this paper we instead focus on surfaces in the image and address the colour constancy problem by unsupervised learning of an appropriate model for each training surface in training images. We find nearest neighbour models for each surface in a test image and estimate its illumination based on comparing the statistics of pixels belonging to nearest neighbour surfaces and the target surface. The final illumination estimation results from combining these estimated illuminants over surfaces to generate a unique estimate. The proposed method has the advantage of overcoming multi-illuminant situations, which is not possible for most current methods. The concept proposed here is a completely new approach to the colour constancy problem. We show that it performs very well, for standard datasets, compared to current colour constancy algorithms.

[1]  Tom Minka,et al.  Bayesian Color Constancy with Non-Gaussian Models , 2003, NIPS.

[2]  Joost van de Weijer,et al.  Color constancy based on the Grey-edge hypothesis , 2005, IEEE International Conference on Image Processing 2005.

[3]  Jitendra Malik,et al.  Shape Context: A New Descriptor for Shape Matching and Object Recognition , 2000, NIPS.

[4]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[5]  Steven D. Hordley,et al.  Scene illuminant estimation: Past, present, and future , 2006 .

[6]  Joost van de Weijer,et al.  Generalized Gamut Mapping using Image Derivative Structures for Color Constancy , 2008, International Journal of Computer Vision.

[7]  Antonio Torralba,et al.  Nonparametric scene parsing: Label transfer via dense scene alignment , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Brian V. Funt,et al.  A Large Image Database for Color Constancy Research , 2003, CIC.

[9]  Andrew Zisserman,et al.  Classifying Images of Materials: Achieving Viewpoint and Illumination Independence , 2002, ECCV.

[10]  Antonio Torralba,et al.  Ieee Transactions on Pattern Analysis and Machine Intelligence 1 80 Million Tiny Images: a Large Dataset for Non-parametric Object and Scene Recognition , 2022 .

[11]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[12]  Mark S. Drew,et al.  Diagonal transforms suffice for color constancy , 1993, 1993 (4th) International Conference on Computer Vision.

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

[14]  Theo Gevers,et al.  Color Constancy Using Natural Image Statistics and Scene Semantics , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Brian V. Funt,et al.  Committee-Based Color Constancy , 1999, CIC.

[16]  E. Land The retinex theory of color vision. , 1977, Scientific American.

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

[18]  Andrew Blake,et al.  Bayesian color constancy revisited , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  David A. Forsyth,et al.  A Novel Approach To Colour Constancy , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[20]  Keigo Hirakawa,et al.  Color constancy beyond bags of pixels , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  G. Buchsbaum A spatial processor model for object colour perception , 1980 .

[22]  Krista A. Ehinger,et al.  SUN database: Large-scale scene recognition from abbey to zoo , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[23]  Trevor Darrell,et al.  Fast pose estimation with parameter-sensitive hashing , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[24]  Alexei A. Efros,et al.  Ensemble of exemplar-SVMs for object detection and beyond , 2011, 2011 International Conference on Computer Vision.

[25]  W. Marsden I and J , 2012 .

[26]  D. Kibler,et al.  Instance-based learning algorithms , 2004, Machine Learning.

[27]  Graham D. Finlayson,et al.  Shades of Gray and Colour Constancy , 2004, CIC.

[28]  Jun Sun,et al.  Color constancy based on texture pyramid matching and regularized local regression. , 2010, Journal of the Optical Society of America. A, Optics, image science, and vision.

[29]  Jitendra Malik,et al.  Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons , 2001, International Journal of Computer Vision.

[30]  Andrew Zisserman,et al.  A Statistical Approach to Texture Classification from Single Images , 2004, International Journal of Computer Vision.

[31]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..