Journal Home > Volume 18 , Issue 1
Tsinghua Science and Technology 2013, 18(1): 51-56 https://doi.org/10.1109/TST.2013.6449407
Open Access | Issue | Published: 07 February 2013

C-HMAX: Artificial Cognitive Model Inspired by the Color Vision Mechanism of the Human Brain

Show Author's Information Bo Yang,  Lipu Zhou,  Zhidong Deng( )
State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
Keywords:
machine learning, artificial cognitive model, traffic sign recognition
Cite this article:
Yang B, Zhou L, Deng Z. C-HMAX: Artificial Cognitive Model Inspired by the Color Vision Mechanism of the Human Brain. Tsinghua Science and Technology, 2013, 18(1): 51-56. https://doi.org/10.1109/TST.2013.6449407
Download citation
EndNote(RIS)
BibTeX

477

Views

27

Downloads

Citations

8

Crossref

N/A

WoS

10

Scopus

0

CSCD

Abstract Full text About this article

Artificial cognitive models and computational neuroscience methods have garnered great interest from both neurologist and leading analysts in recent years. Among the cognitive models, HMAX has been widely used in computer vision systems for its robustness shape and texture features inspired by the ventral stream of the human brain. This work presents a Color-HMAX (C-HMAX) model based on the HMAX model which imitates the color vision mechanism of the human brain that the HMAX model does not include. C-HMAX is then applied to the German Traffic Sign Recognition Benchmark (GTSRB) which has 43 categories and 51 840 sample traffic signs with an accuracy of 98.41%, higher than most other models including linear discriminant analysis and multi-scale convolutional neural network.


menu
Abstract
Full text
Outline
About this article

C-HMAX: Artificial Cognitive Model Inspired by the Color Vision Mechanism of the Human Brain

Show Author's information Bo Yang, Lipu Zhou, Zhidong Deng( )
State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China

Abstract

Artificial cognitive models and computational neuroscience methods have garnered great interest from both neurologist and leading analysts in recent years. Among the cognitive models, HMAX has been widely used in computer vision systems for its robustness shape and texture features inspired by the ventral stream of the human brain. This work presents a Color-HMAX (C-HMAX) model based on the HMAX model which imitates the color vision mechanism of the human brain that the HMAX model does not include. C-HMAX is then applied to the German Traffic Sign Recognition Benchmark (GTSRB) which has 43 categories and 51 840 sample traffic signs with an accuracy of 98.41%, higher than most other models including linear discriminant analysis and multi-scale convolutional neural network.

Keywords: machine learning, artificial cognitive model, traffic sign recognition

References(16)

[1]
D. J. Ingle, M. A. Goodale, and R. J. W. Mansfield, Analysis of Visual Behavior. Boston, America: MIT Press, 1982.
[2]
M. A. Goodale and A. D. Milner, Separate visual pathways for perception and action, Trends in Neuroscience, vol. 15, no. 1, pp.20-25, Jan. 1992.
DOI Google Scholar
[3]
J. Jin, Y. Wang, H. A. Swadlow, and J. M. Alonso, Population receptive fields of ON and OFF thalamic inputs to an orientation column in visual cortex, Nat. Neurosci., vol. 14, no. 2, pp.232-238, Jan. 2011.
DOI Google Scholar
[4]
M. S. Gazzaniga, R. B. Ivry, and G. R. Mangun, Cognitive Neuroscience, 2nd Ed. New York, America: W W Norton & Co Inc (Np), 2002.
[5]
T. J. Bussey and L. M. Saksida, Memory, perception, and the ventral visual-perirhinal-hippocampal stream: Thinking outside of the boxes, Hippocampus, vol. 17, no. 9, pp.898-908, Sep. 2007.
DOI Google Scholar
[6]
T. M. Preuss, I. Stepniewska, and J. H. Kaas, Movement representation in the dorsal and ventral premotor areas of owl monkeys: A microstimulation study, J. Comp. Neurol., vol. 371, no. 4, pp.649-676, Aug. 1996.
DOI
[7]
R. Gattas, A. P. Sousa, M. Mishkin, and L. G. Ungerleider, Cortical projections of area V2 in the Macaque, Cereb. Cortex., vol. 7, no. 2, pp.110-129, Jul. 1997.
DOI Google Scholar
[8]
D. Y. Ts’o, M. Zarella, and G. Burkitt, Whither the hypercolumn, Journal of Physiology, vol. 587, no. 12, pp.2791-2805, Jun. 2009.
DOI Google Scholar
[9]
M. Riesenhuber and T. Poggio, Hierarchical models of object recognition in cortex, Nature Neuroscience, vol. 2, no. 11, pp.1019-1025, Feb. 1999.
DOI Google Scholar
[10]
T. Serre and T. Poggio, Reverse-engineering the brain, Communications of the Association for Computing Machinery, vol. 53, no. 10, pp.54-61, Oct. 2010.
DOI Google Scholar
[11]
T. Serre, L. Wolf, and T. Poggio, Object recognition with features inspired by visual cortex, presented at the 2005 IEEE Conference on Computer Vision and Pattern Recognition, San Diego, USA, 2005.
DOI
[12]
J. Mutch and D. G. Lowe, Multiclass object recognition with sparse, localized features, presented at the 2006 IEEE Conference on Computer Vision and Pattern Recognition, New York, USA, 2006.
[13]
N. W. Daw, Goldfish Retina: Organization for simultaneous color contrast, Science, vol. 158, no. 3803, pp. 942-944, Nov. 1967.
DOI Google Scholar
[14]
B. R. Conway, Neural Mechanisms of Color Vision: Double-Opponent Cells in the Visual Cortex. Dordrecht, Netherlands: Kluwer Academic Press, 2002.
DOI
[15]
J. E. Dowling, Neurons and Networks: An Introduction to Behavioral Neuroscience, 2nd Ed. Massachusetts, USA: Belknap Press of Harvard University Press, 2001.
[16]
J. Stallkamp, M. Schlipsing, J. Salmen, and C. Igel, Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition, Neural Networks, vol. 32, no. 1, pp. 323-332, Aug. 2012.
DOI Google Scholar
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Received: 15 October 2012
Accepted: 19 December 2012
Published: 07 February 2013
Issue date: February 2013

Copyright

© The author(s) 2013

Acknowledgements

This work was supported in part by the National Natural Science Foundation of China (Nos. 90820305, 60775040, and 61005085) and Aeronautical Science Foundation of China (No. 2010ZD01003).

Rights and permissions

Return