Abstract
Biological vision provides an excellent promise in the design of automated object recognition (AOR) system. A particularly important unresolved issue is that of learning. This topic is also explored in Chapters (Choe) and (Perlovsky), where learning is related to actions (Choe) and to the knowledge instinct (Perlovsky). Reinforcement learning (RL) is part of procedural learning that is routinely employed in biological vision. The RL in biology appears to be crucial for attentive decision making process in a stochastic dynamic environment. RL is a learning mechanism that does not need explicit teacher or training samples, but learns from an external reinforcement. The idea of RL is related to the knowledge instinct explored in Chapter (Perlovsky), which provides internal motivations for matching models to sensor signals. The model in this chapter implements RL through neural networks in an adaptive critic design (ACD) framework in automatic recognition of objects. An ACD approximates the neuro-dynamic programming employing an action and a critic network, respectively. Two ACDs such as Heuristic Dynamic Programming (HDP) and Dual Heuristic dynamic Programming (DHP) are both exploited in implementing the RL model. We explore the plausibility of RL for distortion-related object recognition inspired by principles of biological vision. We test and evaluate these two designs using simulated transformations as well as face authentication problems. Our simulations show promising results for both designs for transformation-invariantAOR.
Keywords
- Biologically inspired model · Reinforcement learning (RL) · Automated object recognition (AOR) · Heuristic dynamic programming (HDP) · Dual Heuristic Dynamic programming (DHP) · Image transformation · Face authentication
This is a preview of subscription content, access via your institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Casasent, D., Psaltis, D.:Position, rotation and scale invariant optical correlator. Appl. Opt. 15 ((1976) 1795–1799
Iftekharuddin, K. M., Ahmed, F., Karim, M.A.: Amplitude-coupled mace for automatic target recognition applications. Opt. Engr. 35 ((1996) 1009–1014
Fuji, H., Almeida, S.P., Dowling, J.E.: Rotational matched spatial filter for biological pattern recognition. Appl. Opt. 19 ((1980) 1190–1195
Diab, S.L., Karim, M.A., Iftekharuddin, K.M.: Multi-object detection of targets with fine details, scale and translation variations. Opt. Engr. 37 ((1998) 876–883
Wei, G.Q., Qian, J., Schramm, H.: A dual dynamic programming approach to the detection of spine boundaries. Lecture Notes In Computer Science, Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention 2208 ((2001) 524–531
Schmid, C., Mohr, R.: Matching by local invariants. Reseach report, robotics, image and vision N2644, INRIA-Rhône-Alps, 46 Ave Felix Viallet, 38031 Grenoble Cedex 1 (France) (1995)
Bryant, M.L., Worrell, S.W., Dixon, A.C.: MSE template size analysis for MSTAR data. In Zelnio, E.G., ed.: Algorithms for synthetic aperture radar imagery V, Proc. of SPIE. Volume 3370. ((1998) 396–405
Iftekharuddin, K.M., Power, G.: A biological model for distortion invariant target recognition. In: Proc. of IJCNN, Washington DC, U.S.A., IEEE Press (2001) 559–564
Iftekharuddin, K.M., Rentala, C., Dani, A.: Determination of exact rotation angle and discrimination for rotated images. Optics & Laser Technology 34 ((2002) 313–327
Iftekharuddin, K.M., Malhotra, R.P.: Role of multiresolution attention in automated object recognition. In: Proc. of IJCNN, Hawaii, U.S.A., IEEE Press ((2002) 2225–2230
Iftekharuddin, K.M., Widjanarko, T.: Reinforcement learning in multiresolution object recognition. In: Proc. of IJCNN. Volume 2., Hawaii, U.S.A., IEEE Press (2004) 1085–1090
Siddiqui, F., Iftekharuddin, K.M.:Multiresolution object recognition using dual heuristic programming. In: Proc. of IJCNN. (2006)
Ge, Z.:Automated target recognition by reinforcement learning without a prior model. Ph.D. thesis, Texas Technological University, Lubbock, TX, USA (1997)
Sutton, R.S., Barto, A.G., Williams, R.J.: Reinforcement learning is direct adaptive optimal control. In: Proceedings of 1991 IEEE American Control Conference. (1991)
Tsitsiklis, J.N., Van Roy, B.: Feature-based methods for large scale dynamic programming. In: Machine Learning. Volume 22. Springer Netherlands ((1994) 59–94
Marbach, P., Tsitsiklis, J.N.: Simulation-based optimization of markov reward processes. IEEE Trans. Auto. Contr. 46 (2) ((2001) 191–209
Van Roy, B.: Neuro-dynamic programming: overview and recent trends. Handbook of Markov Decision Processes: Methods andApplications (2001)
Bertsekas, D.P.: Dynamic programming: deterministic and stochastic models. Printice Hall, Englewood Cliffs, NJ, U.S.A. (1987)
Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-dynamic programming. Athena Scientific, Belmont, MA (1996)
Ens, R., Si, J.: Apache helicopter stabilization using neuro dynamic programming. Report G6316, AIAA (2000)
Si, J., Wang, Y.T.: On-line learning control by association and reinforcement. IEEE Trans. Neural Networks 12(2) ((2001) 264–276
Venayagamoorthy, G.K., Harley, R.G., Wunsch, D.C.: Implementation of adaptive critic based neurocontrollers for turbogenerators in a multimachine power system. IEEE Trans. Neural Networks 15(5) ((2003) 1047–1064
Liu, W., Venayagamoorthy, G.K., Wunsch, D.C.: A heuristic dynamic programming based power system stabilizer for a turbogenerator in a single machine power system. In: IEEE-IAS $38th$ Annual Meeting. (2003)
Prokhorov, D., Wunsch, D.C.: Adaptive critic designs. IEEE Trans. Neural Networks 8 (5) ((1997) 997–1007
Bellman, R.E.: Dynamic programming. Princeton University Press, Princeton, NJ, U.S.A. (1957)
Iftekharuddin, K.M.: Attention-driven object recognition. Final report AFSOR Grant# F33615-01-C-1985, Wright Patterson AF Lab (2001)
Schultz, W.: Predictive reward signal of dopamine neuron. J. Neurophysiology 80 ((1998) 1–27
Graham, D.B., Allinson, N.M.: Characterizing virtual eigensignatures for general purpose face recognition. In H. Wechsler, P. J. Phillips, V.B.F.F.S., Huang, T.S., eds.: Face Recognition: From Theory to Applications. Volume 163 of F, Computer and Systems Sciences. NATO ASI ((1998) 446–456
K.Chang, K.W.B., Flynn, P.J.: Face recognition using 2d and 3d facial data. In: ACM Workshop on Multimodal User Authentication. ((2003) 25–32
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Iftekharuddin, K.M., Li, Y., Siddiqui, F. (2007). A Biologically Inspired Dynamic Model for Object Recognition. In: Perlovsky, L.I., Kozma, R. (eds) Neurodynamics of Cognition and Consciousness. Understanding Complex Systems. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73267-9_10
Download citation
DOI: https://doi.org/10.1007/978-3-540-73267-9_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73266-2
Online ISBN: 978-3-540-73267-9
eBook Packages: Physics and AstronomyPhysics and Astronomy (R0)