Learning Human-Like Color Categorization through Interaction

Human perceives color in categories, which may be identified using color name such as red, blue, etc. The categorization is unique for each human being. However despite the individual differences, the categorization is shared among members in society. This allows communication among them, especially when using color name. Sociable robot, to live coexist with human and become part of human society, must also have the shared color categorization, which can be achieved through learning. Many works have been done to enable computer, as brain of robot, to learn color categorization. Most of them rely on modeling of human color perception and mathematical complexities. Differently, in this work, the computer learns color categorization through interaction with humans. This work aims at developing the innate ability of the computer to learn the human-like color categorization. It focuses on the representation of color categorization and how it is built and developed without much mathematical complexity.

Authors:

• Rinaldo Christian Tanumara
• Ming Xie
• Chi Kit Au

Keywords:

• Color categorization
• color learning
• machinelearning
• color naming.

References:

[1] R. W. Hunt, Measuring Colour. Fountain Press, 1998.
[2] L. Steels and T. Belpame, "Coordinating perceptually grounded
categories through language: A case study for colour," Behavioral and
Brain Sciences, vol. 28, pp. 469-529, 2005.
[3] C. Breazeal, "Toward Sociable Robot," Robotics and Autonomous
Systems, vol. 42, pp. 167-175, 2003.
[4] B. Berlin and P. Kay, Basic color terms: Their universality and
evolution. University of California Press, 1969.
[5] P. Kay and T. Regier, "Resolving the question of color naming
universals," Proceedings of the National Academy of Science, vol. 100,
no. 15, pp. 9085-9089, 2003.
[6] S. Pinker, The language instinct: How the mind creates language. Harper
Perennial Modern Classics, 2000.
[7] E. Rosch-Heider, "Universals in Color Naming and Memory," Journal of
Experimental Psychology, vol. 93, pp. 10-20, 1972.
[8] S. N. Yendrikhovskij, "Computing color categories for statistics of
natural image," Journal of Imaging Science and Technology, vol. 45, no.
5, pp. 409-417, 2001.
[9] A. VanWijk, "A cross-cultural theory of colour and brightness
nomenclature," Bijdragen tot de taal-, land- en volkenkunde, vol. 115,
pp. 113-137, 1959.
[10] T. Belpaeme, "Simulating the formulation of color categories," presented
at International Joint Conference on Artificial Intelligence, Seattle, 2001.
[11] I. R. Davies and G. Corbett, "A cross-cultural study of color grouping:
Evidence for weak linguistic relativity," British Journal of Psychology,
vol. 88, pp. 493-517, 1997.
[12] K. A. Jameson and N. Alvarado, "The relational correspondence
between category exemplars and names," Philosophical Psychology, vol.
10, no. 1, pp. 25-49, 2003.
[13] M. Dowman, "Colour terms, syntax and bayes modelling acquisition and
evolution," PhD Thesis, University of Sydney, 2004.
[14] J. M. G. Lammens, "A computational model of color perception and
color naming," PhD Thesis, State University of New York, 1994.
[15] M. Xie, J. S. Kandhasamy, and H. F. Chia, "Meaning-centric Framework
for Natural Text/Scene Understanding by Robots," International Journal
of Humanoid Robotics, vol. 1, no. 2, pp. 375-407, 2004.
[16] S. Harnad, S. J. Hanson, and J. Lubin, "Learned categorical perception in
neural nets: Implication for symbol grounding," in Symbolic Processors
and Connectionist Network Models in Artificial Intelligence and
Cognitive Modeling: Steps Toward Principled Integration, V. Honavar
and L. Uhr, Eds. Boston: Academic Press, 1995, pp. 191-206.
[17] S. Usui, S. Nakauchi, and M. Nakano, "Reconstruction of Munsell Color
Space by a Five Layered Neural Network," presented at IEEE
International Conference on Neural Network, 1990.
[18] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal
representation by back-propagating errors," Nature, vol. 323, pp. 533-
536, 1986.
[19] X. Yin, D. Guo, and M. Xie, "Hand image segmentation using color and
RCE neural network," Robotics and Autonomous Systems, vol. 34, pp.
235-250, 2001.
[20] N. C. Yeo, K. H. Lee, Y. V. Venkatesh, and S. H. Ong, "Colour image
segmentation using the self-organizing map and adaptive resonance
theory," Image and Vision Computing, vol. 23, pp. 1060-1079, 2005.
[21] A. H. Dekker, "Kohonen neural network for optimal color quantization,"
Network: Computation in Neural System, vol. 5, pp. 351-367, 1994.
[22] T. Uchiyama and M. A. Arbib, "Color Image Segmentation Using
Competitive Learning," IEEE Transaction on Pattern Analysis and
Machine Intelligence, vol. 16, no. 12, pp. 1197-1206, 1994.
[23] A. Verikas, K. Malmqvist, M. Bachauskene, L. Bergman, and K.
Nilsson, "Hierarchical neural network for color classification," presented
at IEEE International Conference on Neural Network, 1994.
[24] S. Dehaene, "Evolution of human cortical circuits for reading and
arithmetic: The "neuronal recycling" hypothesis.," in From Monkey
Brain to Human Brain, S. Dehaene, J. R. Duhamel, M. Hauser, and G.
Rizzolati, Eds. Massachusettes: MIT Press, 2004.
[25] M. D. Hauser, N. Chomsky, and W. T. Fitch, "The faculty of language:
what is it, who has it, and how did it evolve?," in Science, vol. 298,
2002, pp. 1569-1579.
[26] M. Fairchild, Color appearance model. Addison-Wesley, 1998.
[27] P. Kay and L. Maffi, "Color appearance and the emergence and
evolution of basic color lexicons," American Anthropologist, vol. 101,
no. 4, pp. 743-760, 1999.
[28] J. Davidoff, "Language and perceptual categorization," Trends in
Cognitive Sciences, vol. 5, no. 9, pp. 382-387, 2001.
[29] J. Davidoff, I. Davies, and D. Roberson, "Color categories in a stone-age
tribe," Nature, vol. 398, pp. 203-204, 1999.
[30] S. Grossberg and D. Todorovic, "Neural dynamics of 1-D and 2-D
brightness perception: A unified model of classical and recent
phenomena," Perception and Psychophysics, vol. 43, pp. 241-277, 1988.