Data processing: artificial intelligence – Neural network – Learning task
Reexamination Certificate
2006-09-01
2009-10-20
Vincent, David R (Department: 2129)
Data processing: artificial intelligence
Neural network
Learning task
C706S062000
Reexamination Certificate
active
07606777
ABSTRACT:
An artificial visual recognition system and method employ a digital processor and a model executed by the digital processor. The model has a loose hierarchy of layers. Each layer, from a lowest hierarchy level to a top level, provides relatively increasing selectivity and invariance of the input image. The hierarchy allows bypass routes between layers. On output, the model produces feature recognition and classification of an object in the input image. In some embodiments, windowing means provide windows of the input image to the model, and the model responds to shape-based objects in the input image. In another feature, segmenting means segment the input image and enables the model to determine texture-based objects in the input image.
REFERENCES:
patent: 4941122 (1990-07-01), Weideman
patent: 2814572 (2002-03-01), None
Elements of artificial neural networks: Mehrotra, 1997, MIT Press, p. 19.
Bileschi, S. and L. Wolf, “A Unified System for Object Detection, Texture Recognition, and Context Analysis Based on the Standard Model Feature Set,” presented at the 2005 British Machine Vision Conference held at Oxford Brookes University, Sep. 5-8, 2005, published inBritish Machine Vision Conference(BMVC) 2006.
Serre, T. et al., “Object Recognition with Features Inspired by Visual Cortex,”Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Jun. 20-25, 2005 (pp. 994-1000).
Lourens, T. et al., “Large scale natural vision simulations,”Future Generation Computer Systems 10(1994) pp. 351-368.
Stoecker, M. et al., “Size and position invariant visual representation supports retinotopic maps via selective backward paths: A dynamic second order neural network model for a possible functional role of recurrent connections in the visual cortex,”Neurocomputing 17(1997), pp. 111-132.
Wang, R., “A hybrid learning network for shift, orientation, and scalin invariant pattern recognition,”Network: Computation in Neural Systems 12(4):493-512 (2001).
Deco, G. and E.T. Rolls, “A Neurodynamical cortical model of visual attention and invariant object recognition,”Vision Research 44:621-642 (2004).
Rolls, E.T., “Brain mechanisms for invariant visual recognition and learning,”Behavioural Processes, 33:113-138 (1994).
Neven, H. and A. Aertsen, Rate coherence and event coherence in the visual cortex: a neuronal model of object recognition,Biologic Cybernetics 67: 309-322 (1992).
Draper, B. et al., “Implementing the expert object recognition pathway,”Machine Vision and Applications, 16 :27-32 (2004).
Olshausen, B.A. et al., “A Neurological Model of Visual Attention and Invariant Pattern Recognition Based on Dynamic Routing of Information,”The Journal of Neuroscience, 13(11):4700-4719, 1993.
Bulthoff, H. H. et al., “Biologically Motivated Computer Vision,”Second International Workshop, BMCV 2002, pp. 387-397.
Kirstein, S. et al., “Online Learning for Object Recognition with a Hierarchical Visual Cortex Model,”15th International Conference on Artificial Neural Networks(ICANN 2005), pp. 487-492, InArtificial Neural Networks: Biological Inspirations—ICANN 2005, Proceedings, Part I, Duch, W. et al. eds. Springer-Verlag Berlin.
Morikawa, K. and B. Mel, “Seemore: A model of object recognition in the extrastriate visual pathways,”Society for Neuroscience Abstracts 21(1-3):p. 662 (1995).
Porterfield, J.R., “Region Detection Using a Model of Visual Cortex in the Cat,” Dissertation submitted to the Graduate School of the University of Massachusetts, Feb. 1985.
Cahn, D.F., “Pattern Recognition in Learning Models of Visual Cortex: Capabilities and Limits of Candidate Coding Techniques,” Dissertation submitted to the Graduate Division of the University of California, Berkeley, 1975.
Bileschi Stanley M.
Poggio Tomaso
Riesenhuber Maximilian
Serre Thomas
Wolf Lior
Coughlan Peter
Hamilton Brook Smith & Reynolds P.C.
Massachusetts Institute of Technology
Vincent David R
LandOfFree
High-performance vision system exploiting key features of... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with High-performance vision system exploiting key features of..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and High-performance vision system exploiting key features of... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4065666