A biologically inspired system for fast handwritten digit recognition

Proceedings - International Conference on Image Processing, ICIP

Volumn , Issue , 2011, Pages 1749-1752

  Wang, Zhe ^a   Huang, Yaping ^a   Luo, Siwei ^a   Wang, Liang ^a  

^a BEIJING JIAOTONG UNIVERSITY   (China)

Author keywords

complex cell; feature extraction; invariant feature; MNIST database

Indexed keywords

BIOLOGICALLY INSPIRED SYSTEMS; CLASSIFICATION RESULTS; DESCRIPTORS; DIGIT RECOGNITION; FEATURE DESCRIPTORS; GENERATIVE MODEL; HANDWRITTEN DIGIT RECOGNITION; INPUT DATAS; INVARIANT DESCRIPTORS; INVARIANT FEATURES; INVARIANT REPRESENTATION; MINIMIZING ENERGY; MNIST DATABASE; SIMPLE SYSTEM; TEST DATA; UNSUPERVISED ALGORITHMS; VISUAL CORTEXES;

ALGORITHMS; CELLS; CHARACTER RECOGNITION; DATA PROCESSING; IMAGE PROCESSING; INFERENCE ENGINES;

FEATURE EXTRACTION;

EID: 84863065209     PISSN: 15224880     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICIP.2011.6115798     Document Type: Conference Paper

References (15)

1. K. Kavukcuoglu, M. Ranzato, R. Fergus, and Y. LeCun, "Learning invariant features through topographic filter maps," In Proc. of Computer Vision and Pattern Recognition, IEEE, 2009, pp.1605-1612.
2. J.M. Alonso, L.M. Martinez, "Functional connectivity between simple cells and complex cells in cat striate cortex," Nature Neuroscience, 1(5):395-403, 1998.
3. I. Lampl, D. Ferster, T. Poggio, et al. "Intracellular measurements of spatial integration and the MAX operation in complex cells of the cat primary visual cortex." J. Neurophysiology, vol.92, pp. 2704-2713, 2004. (Pubitemid 40340483)
4. A. Hyvärinen, P.O. Hoyer, "A two-layer sparse coding model learn simple and complex cell receptive fields and topography from natural images," Vision Research, 41(18):2413-2423, 2002. (Pubitemid 32667541)
5. A. Hyvärinen, "Fast and robust fixed-point algorithms for independent component analysis," IEEE Transactions on Neural Networks, 10(3):626-634, 1999.
6. A. Hyvärinen, R.Cristescu, and E. Oja, "A fast algorithm for estimating overcompletes ICA bases for image windows," International Joint Conference on Neural Networks, IEEE, 1999, vol.2, pp. 894-899.
7. S. Osindero, M.Welling and G.E. Hinton, "Topographic product models applied to natural scene statistics," Neural Computation, 18(2):381-344, 2006.
8. B. A. Olshausen and D. J. Field. "Sparse coding with an overcomplete basis set: a strategy employed by V1? " Vision Research, 37(23):3311-3325, 1997.
9. N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," In Proc. of Computer Vision and Pattern Recognition, IEEE, 2005, pp.886-893. (Pubitemid 43897286)
10. D. Lowe, "Distinctive image features from scale-invariant keypoints," International Journal of Computer Vision, 60(2):91- 110, 2004.
11. M. Ranzato, C. Poultney, S. Chopra, and Y. LeCun,"Efficient learning of sparse representations with an energy-based model," In Advances in Neural Information Processing Systems, MIT Press, 2006.
12. T. Martinetz, K. Labusch, and D. Schneegaß, "Soft-Double- MaxMinOver: perceptron-like training of support vector machines," IEEE Transactions on Neural Networks, 20(7):1061-1072, 2009.
13. A. Borji, M. Hamidi, F. Mahmoudi,"Robust handwritten character recognition with features inspired by visual ventral stream,"Neural processing letters. 28(2), 97-111, 2008.
14. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, 86(11):2278-2324, 1998.
15. K. Jarrett, K. Kavukcuoglu, M. Ranzato, and Y. LeCun, "What is the best multi-stage architecture for object recognition?" In Proc. International Conference on Computer Vision, IEEE, 2009.