**6. Conclusion and future work**

64 Advances in Object Recognition Systems

classification values to be class 1 T 240 false and class 2 T 240 false . We constrained true-class 1 of the Jaguar S-type object images to unit correlation peak-height constraint, true-class 2 of the Ferrari Testarossa car to half-a-unit correlation peak-height constraint, and false-class 1 and false-class 2 to zero correlation peak-height constraints in the synthesis of the M-HONN system's composite image. Fig. 16 shows the locked window unit of chosen size 70x70 on top of the maximum correlation peak-height values. With the dashed line we have shown the secondary correlation peaks of the output plane and with the solid line we have shown the maximum correlation peak-height value of the output plane. M-HONN system successfully suppressed the unknown background clutter throughout the length of the video sequence and recognised correctly class 1 and class 2 objects. It is emphasised that we

have not included any background information in the training set of the system.

**Class 1: Jaguar S-**

Fig. 15. (Adapted by Kypraios et al., 2009) It shows (a) for the first output layer neuron, and (b) for the second output layer neuron the isometric output correlation plane response of the M-HONN system for Class 1 (normalised to the maximum correlation plane peak-height value), and (c) and (d) the isometric output correlation plane response of the M-HONN system for Class 2 (normalised to the maximum correlation plane peak-height value).

(d) (c)

(a) (b)

**Class 2: Ferrari** 

We have described the design and implementation of the M-HONN system. In particular, we focused in the design and implementation of the M-HONN system for multiple objects recognition of the same and of different classes. The inherited shift invariance properties by the optical correlator block of the system can accommodate for the recognition of multiple objects of the same class. The cross-correlation of each masked test set image with the transformed reference kernel returns an output correlation plane peak value for each cross-correlation step. Thus, the maximum peak height values of the output correlation plane correspond to the recognised true-class objects. By augmenting the output layer of the NNET block of the M-HONN system we can accommodate for the recognition of multiple objects of different classes. In effect, we increase the number of the output layer neurons proportionally with the number of the different object classes. We assign one output neuron to each different class. It was proven experimentally that by choosing different values of the classification levels for the true-class ClT and false-class ClF objects we can control the M-HONN system's behaviour and it can be varied from more like a high-pass biased filter, which generally gives sharp correlation peaks and good clutter suppression but is more sensitive to intra-class distortions, to more like a MVSDF filter behaviour, which generally gives broader correlation peaks but is more robust to intra-class distortions of the input objects.

We have assessed the performance of the M-HONN system by conducting several series of tests. We assessed the system's ability to detect non-training in-class images that are oriented at the intermediate angle of view between the training images. From the recorded

Performance Analysis of

**7. References** 

transformed images into its composite image synthesis.

*Neural Networks,* Vol.3, pp. 453-465

No.3, pp. 914-923

No.3, pp. 392-408

International, Inc.

Vol.13, pp. 837-841

ISBN 0-9717321-0-8, Boston, MA

*Optics*, Vol. 36, No. 35, pp. 9212-9224

pp. 161-168

*Applied Optics,* Vol.23, No.10, 1620-1627

Morgan Kaufmann, pp. 1-8, ISBN 1558607072

*Optical Society of America,* Vol.5, No.4, pp. 562-571

recognition, *Applied Optics,* Vol.08, No.11, 2354-2356

treatment, *Applied Optics,* Vol.19, No.23, 3877-3878

Neural Networks, *Applied Optics,* Vol.26, pp. 4972-4978

images, *Applied Optics*, Vol. 37, No. 11, pp. 2051-2062

the Modified-Hybrid Optical Neural Network Object Recognition System Within Cluttered Scenes 67

processing different angles of the captured data, and incorporating the corresponding

Aler, R., Borrajo, D. & Isasi, P. (2000). Knowledge representation issues in control

Bahri, Z. & Kumar, B. V. K. (1988). Generalized Synthetic Discriminant Functions, *Journal of* 

Beale, R. & Jackson, T. (1990). *Neural Computing : An Introduction*, Institute of Physics Publishing, Hilger, ISBN 0852742622, 9780852742624, Bristol, Philadelphia Bottou, L., Fogelman- Soulié, F., Blanchet, P. & Lienard, J. S. (1990). Speaker Independent

Casasent, D. (1984). Unified synthetic discriminant function computational formulation,

Casasent, D., Neiberg, L. M. & Sipe, M. A. (1998). Feature Space Trajectory Distorted Object

Caulfield, H. J. & Maloney, W. T. (1969). Improved discrimination in optical character

Caulfield, H. J. (1980). Linear combinations of filters for character recognition: a unified

Delopoulos, A., Tirakis, A. & Kollias, S. (1994). Invariant Image Classification Using Triple-

Dobnikar, A., Ficzko J., Podbregar, D. & Rezar, U. (1991/92). Invariant pattern classification

Giles, C. L. & Maxwell, T. (1987). Learning, Invariance and Generalisation in Higher-Order

Hagan, M. T., Demuth, H. B. & Beale, M. H. (1996). *Neural Network Design,* PWS Publishing,

Haykin, S. (1999). *Neural Networks-A Comprehensive Foundations,* 2nd Edition, Prentice Hall

Jamal-Aldin, L. S., Young, R. C. D. & Chatwin, C. R. (1997). Application of non-linearity to

Jamal-Aldin, L. S., Young, R. C. D. & Chatwin, C. R. (1998). Synthetic discriminant function

Kanaoka, T., Chellapa, R., Yoshitaka, M. & Tomita, S. (1992). A Higher-Order Neural

wavelet-transformed images to improve correlation filter performance, *Applied* 

filter employing nonlinear space-domain preprocessing on bandpass-filtered

Network for Distortion Invariant Pattern Recognition, *Pattern Recognition Letters,* 

knowledge learning, *Proceedings of 25th International Conference on Machine Learning*,

Isolated Digit Recognition : Multilayer Perceptrons vs Dynamic Time Warping,

Representation for Classification and Pose Estimation, *Optical Engineering,* Vol.37,

Correlation-Based Neural Networks, *IEEE Transactions on Neural Networks*, Vol.5,

neural network versus FT approach, *Microprocessing and Microprogramming,* Vol. 33,

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 <sup>3</sup> <sup>ˆ</sup> 5 ,40 (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 in-class distortions.

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 Jaguar S-type car.

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 object.

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 processing different angles of the captured data, and incorporating the corresponding transformed images into its composite image synthesis.
