**7. References**

 <sup>3</sup> <sup>ˆ</sup> 5 ,40

66 Advances in Object Recognition Systems

results, we were able to show the system's ability to interpolate well between the intermediate car poses. The system maintained correlation peak sharpness for the in-class training and non-training images. More specifically, the M-HONN system is able to interpolate non-linearly between the reference and non-reference images to follow the activation function graph. The NNET block is able to generalize between all the reference and non-reference images. Next, we have tested the M-HONN system's distortion range. From the recorded results, we have shown that the system has exhibited a high distortion range recognising all the intermediate car poses of the test set over the range

(bisector angle). The third series of tests we conducted were for assessing the discrimination ability of the M-HONN system. From the recorded results, we have shown that the system successfully discriminate between objects of different classes while retaining invariance to

We have analysed the M-HONN system's biologically-inspired hybrid design and we have found to combine a knowledge representation unit being the optical correlator block with a knowledge learning unit being the NNET block, as for the G-HONN type systems. We conducted several experiments for testing the system's problem solving abilities. The M-HONN system was able to solve the visual task of recognising certain Jaguar S-type car poses to belong in the true-class from other Jaguar S-type car poses. Also, the M-HONN system was able to solve the visual task of recognising only the true-class objects of the

The last series of tests aimed to assess the M-HONN system's performance of recognising multiple objects of different classes within clutter. We have tested the system with a recorded video sequence. The system successfully suppressed the unknown background clutter during the whole length of the video sequence and recognised correctly class 1 and class 2 objects. In overall, the M-HONN system was able to correctly recognise true-class objects out-of-plane rotated, translated off-the-centre and inserted into background scenes. It is emphasised that the system was able to recognise the true-class objects within an unknown background clutter scene since we have not included any background information in its training set. Additionally, all the invariance properties were simultaneously exhibited by the M-HONN system with a single pass over the input data sets. In effect, as we could see from its transfer function, M-HONN system is not either a multiple stages-type of filter or any pre-processing of the input data is required for maintaining its invariance properties. There is no need for a separate background segmentation pre-processing stage prior the system's object tracking as in the case of other motion based segmentation and object tracking techniques. Instead, the M-HONN system is able to successfully suppress the background clutter and track throughout the video sequence the recognised true-class

In future, we would like to assess the performance of each output neuron of the M-HONN system's NNET block individually and record separately their performance metrics values for the detectability, distortion range, and discrimination ability. Also, we believe that the M-HONN system's design can be extended to accommodate three-dimensional (3D) object recognition. Similarly to stereo vision systems (Lowe, 1987; Xu & Zhang, 1996; Sumi et al., 2002), the M-HONN system's design can be extended with a second input mask for

in-class distortions.

Jaguar S-type car.

object.


Performance Analysis of

the Modified-Hybrid Optical Neural Network Object Recognition System Within Cluttered Scenes 69

Lee, I. & Portier, B. (11-13 July 2007). An empirical study of knowledge representation and

Lowe, D. G. (1987). Three-dimensional object recognition from single two dimensional

Lynn, P. A. & Fuerst, W. (1998). *Introductory Digital Signal Processing- with Computer* 

Mahalanobis, A., Kumar, B. V. K., Song, S., Sims, S. R. F. & Epperson, J. F. (1994). Unconstrained Correlation Filters, *Applied Optics,* Vol.33, No.17, pp. 3751-3759 Nguyen, D. & Widrow, B. (1989). The Truck Backer-Upper: An Example of Self-Learning in

Nguyen, D. & Widrow, B. (1990). Improving the Learning Speed of 2-Layer Neural

Proakis, J. G. & Manolakis, D. G. (1988). *Introduction to Digital Signal Processing,* Prentice Hall

Refregier, Ph. (1990). Filter design for optical pattern recognition: multicriteria optimisation

Refregier, Ph. (1991). Optimal trade-off filters for noise robustness, sharpness of the correlation peak and Horner efficiency, *Optics Letters,* Vol. 16, No. 11, pp. 829-831 Shvedov, A., Schmidt, A. & Yakubovich, V. (1979). Invariant Systems of Features in Pattern

Simard, P. & LeCun, Y. (1992). Reverse TDNN : An Architecture for Trajectory Generation,

Spirkovska, L. & Reid, M. (1992). Robust Position, Scale and Rotation Invariant Object

Stamos, E. (2001). *Algorithms for Designing Filters for Optical Pattern Recognition,* D.Phil.

Sumi, Y., Kawai, Y., Yoshimi, T. & Tomita, F. (2002). 3D Object recognition in cluttered

Talukder, A. & Casasent, D. (1999). Non-Linear Features for Product Inspection, *Optical* 

The Mathworks (August 2008). Neural Network Processing Toolbox 13: User's Guide for

Vander Lugt, A. (1964). Signal Detection By Complex Spatial Filtering, *IEEE Transactions on* 

*Pattern Recognition X, Proceedings of SPIE,* Vol.3715, pp. 32-43

version Matlab 6.5, Available from http://www.mathworks.com

*Advances in Neural Information Processing Systems,* Moody, J., Hanson, S. & Lipmann,

Recognition Using Higher-Order Neural Networks, *Pattern Recognition,* Vol.25, pp.

Thesis, Department of Electronic and Electrical Engineering, University College

environments by segment-based stereo vision, *International Journal of Computer* 

*IEEE International Joint Conference on Neural Networks,* Vol.3, pp. 21-26 Perantonis, S. & Lisboa, P. (1992). Translation, Rotation and Scale Invariant Pattern

*Transactions on Neural Networks,* Vol.3, No.2, pp. 241-251

approach, *Optics Letters*, Vol*.* 15, No. 15, pp. 854- 856

R., Morgan Kauffmann, Vol.4, pp. 579-588

*Vision, Springer,* Vol. 46, No. 1, pp. 5-23

*Information Theory,* Vol.10, pp. 139-145

975-985

London

Recognition, *Automation Remote Control,* Vol. 40, pp. 131-142

Neural Networks, *Proceedings of the IEEE International Joint Conference on Neural* 

Networks by Choosing Initial Values of the Adaptive Weights, *Proceedings of the* 

Recognition by High-Order Neural Networks and Moment Classifiers, *IEEE* 

*Engineers and Scientists,* Oxford University Press, New York-Oxford

images, *Artificial Intelligence, Elsevier,* Vol. 31, No. 3, pp. 355-395

*Applications,* John Wiley & Sons Ltd.

*Networks,* Vol.2, pp. 357-363

International Paperback Editions

learning within conceptual spaces for intelligent agents, *6th IEEE/ACIS International Conference Computer and Information Science*, pp. 463-468, Melbourne, Australia Looney, C. G. (1997). *Pattern Recognition Using Neural Networks-Theory and Algorithms for* 


68 Advances in Object Recognition Systems

Khotanzad, A. & Hong, H. (1990). Invariant Image Recognition by Zernike Moments, *IEEE Transactions on Pattern Analysis and Machine Intelligence,* Vol. 12, pp. 489-497 Kumar, B. V. K. & Hassebrook, L. (1990) Performance measures for correlation filters,

Kumar, B. V. K. (1986). Minimum Variance Synthetic Discriminant Functions, *Journal Optics* 

Kumar, B. V. K. (1992). Tutorial Survey of Composite Filter Designs for Optical Correlators,

Kypraios, I. (2009). A Comparative Analysis of the Hybrid Optical Neural Network-type

Kypraios, I. (2010). *Hybrid optical neural network-type filters for multiple objects recognition within cluttered scenes,* Object Recognition, InTech, ISBN 978-953-307-222-7 Kypraios, I. (February 2010). A Digital/Optical Neuronal Model for the Cognitive

Kypraios, I., Lei, P. W., Birch, P. M., Young, R. C. D. & Chatwin C. R. (2008). Performance

Kypraios, I., Young, R. C. D. & Chatwin, C. R. (2004b). Performance assessment of

Kypraios, I., Young, R. C. D., Birch, P. M. & Chatwin, C. R. (2004a). Object Recognition

Kypraios, I., Young, R. C. D., Birch, P. M. & Chatwin, C. R. (2003). A non-linear training set

Kypraios, I., Young, R. C. D., Chatwin C. R. (2002). An Investigation of the Non-Linear

LeCun, Y. (1989). Generalisation and Network Design Strategies, *Connectionism in* 

LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., Jackel, L. D.

Filters Performance within Cluttered Scenes, *51st International Symposium ELMAR,* 

Interaction Between Retina Sensor and the Human Brain Visual Cortex, *Poster Presentation, INCF UK Node Congress Analysing and Modelling the Neural Systems in* 

Assessment of the Modified-Hybrid Optical Neural Network Filter, *Applied Optics,* 

Unconstrained Hybrid Optical Neural Network filter for Object Recognition Tasks in Clutter, *Optical Pattern Recognition XV, Proceedings of SPIE,* Vol.5437, pp. 51-62 Kypraios, I., Young, R. C. D. & Chatwin, C. R. (2009). Modified-Hybrid Optical Neural

Network Filter for Multiple Objects Recognition within Cluttered Scenes, *Optics and Photonics for Information Processing III, Proceedings SPIE,* Vol.7442, pp. 74420P-

Within Cluttered Scenes Employing a Hybrid Optical Neural Network Filter, *Optical Engineering Special Issue on Trends in Pattern Recognition,* Vol.43, pp. 1839-

superposition filter derived by neural network training methods for implementation in a shift invariant optical correlator, *Proceedings SPIE Defense & Security, Optical Pattern Recognition XIV,* Vol*.* 5106, pp. 84-95, Orlando, Florida, USA

Properties of Correlation Filter Synthesis and Neural Network Design, *Asian Journal* 

*Perspective,* Pfeirer, R., Schreter, Z., Fogelman-Soulié, F. & Steels, L., Elsevier

(1990). Handwritten Digit Recognition with a Backpropagation Network, *Advances in Neural Information Processing Systems,* Touretzky, D., Morgan Kaufmann, Vol.2,

*Applied Optics*, Vol. 29, No. 20, pp. 2997-3006

*IEEE Region 8/IEEE Croatia/EURASIP,* Vol.1, pp. 71-77

*Health and Disease, Informatics Forum,* Edinburgh

Vol.47, No.18, pp. 3378-3389

*of Physics,* Vol.11, No.3, pp. 313-344

Science, Amsterdam

pp. 396-404

74420P-12

1850

*Society America A,* Vol.3, pp. 1579-1584

*Applied Optics,* Vol.31, No.23, 4773-4801


**Section 2** 

**Colour Processing** 

