A Quantum Multilayer Self Organizing Neural Network for Binary Object Extraction From A Noisy Perspective
DOI:
https://doi.org/10.18486/ijcsnt/3.1.029Keywords:
Multilayer Self-Organizing Neural Network, Binary Object Extraction, Quantum Computing, Quantum Back Propagation Quantum Multilayer Self-Organizing Neural NetworkAbstract
Binary object extraction from a noisy perspective is a challenging proposition in the computer vision community. Various research initiatives based on different methodologies have been entrusted on this aspect over the decades. The multilayer self-organizing neural network (MLSONN) architecture implemented by a fuzzy measure guided backpropagation of errors is one of the best accomplishments in this direction. In this article, a quantum multilayer self-organizing neural network (QMLSONN) architecture is proposed to achieve the same objective. Quantum computation plays a remarkable role in the proposed architecture. The proposed architecture operates using single qubit rotation gates. Here different nodes and interconnection weights act as vital components for this intention. The proposed QMLSONN architecture comprises three processing layers specified as input, hidden and output layers. The nodes in the processing layers are represented by qubits and the interconnection weights are represented by quantum gates. A quantum measurement at the output layer destroys the quantum states of the processed information thereby inducing assimilation of linear indices of fuzziness as the network system errors used to adjust network interconnection weights through a proposed quantum back propagation algorithm. Results of application of the QMLSONN are established on a synthetic and a real life spanner image with various degrees of Gaussian noise and uniform noise. Comparative study with the classical MLSONN architecture reveals the time efficiency of the presented QMLSONN architecture. Moreover, the QMLSONN architecture also restores the shape of the extracted objects to a great extent.
References
Pham DT and Bayro-Corrochano EJ. Neural computing for noise filtering, edge detection and signature extraction. Journal of Systems Engineering 1998; 2(2): 666–670.
Lippmann RP. An introduction to computing with neural nets. IEEE ASSP Magazine 1987; : 3–22. DOI: https://doi.org/10.1109/MASSP.1987.1165576
Haykin S. Neural networks: A comprehensive foundation. second ed. Upper Saddle River, NJ: Prentice Hall, 1999.
Abdallah MA, Samu TI and GrissonWA. Automatic target identification using neural networks. In SPIE Proceedings Intelligent Robots and Computer Vision XIV, volume 2588. pp. 556–565. DOI: https://doi.org/10.1117/12.222708
Antonucci M, Tirozzi B, Yarunin ND et al. Numerical simulation of neural networks with translation and rotation invariant pattern recognition. International Journal of Modern Physics B 1994; 8(11–12): 1529–1541. 14 and 16M. DOI: https://doi.org/10.1142/S0217979294000658
Egmont-Petersen, D. de Ridder, and H. Handels, “Image processing using neural networks - a review,” Pattern Recognition, vol. 35, no. 10, pp. 2279–2301, 2002. DOI: https://doi.org/10.1016/S0031-3203(01)00178-9
Kamgar-Parsi B. Automatic target extraction in infrared images. NRL Rev 1995; : 143–146.
Perlovsky LI, Schoendor WH, Burdick BJ et al. Model-based neural network for target detection in sar images. IEEE Transactions on Image Processing 1997; 6(1): 203–216. DOI: https://doi.org/10.1109/83.552107
Scott PD, Young SS and Nasrabadi NM. Object recognition using multilayer hopfield neural network. IEEE Transactions on Image
Kohonen T. Self-organization and associative memory. London: Springer-Verlag, 1984. Acad. Sci. U. S. pp. 3088–3092.
Hopfield JJ. Neurons with graded response have collective computation of hopfield neural network for associative pattern recognition. Proceedings of SPIE 2001; 4417: 558–562. Fig. 5. DOI: https://doi.org/10.1117/12.441352
Bhattacharyya S and Maulik U. Soft Computing For Image And Multimedia Data Processing. Germany: Springer, 2013. DOI: https://doi.org/10.1007/978-3-642-40255-5
Ghosh A, Pal NR and Pal SK. Self organization for object extraction using a multilayer neural network and fuzziness measures. IEEE Transactions on Fuzzy Systems 1993; 1(1): 54–68. DOI: https://doi.org/10.1109/TFUZZ.1993.390285
Matsui N, Takai M and Nishimura H. A network model based on qubit-like neuron corresponding to quantum circuit. The Institute of Electronics Information and Communications in Japan (Part III: Fundamental Electronic Science) 2000; 83(10): 67–73. DOI: https://doi.org/10.1002/(SICI)1520-6440(200010)83:10<67::AID-ECJC8>3.0.CO;2-H
Kouda N, Matsui N and Nishimura H. A multilayered feedforward network based on qubit neuron model. Systems and Computers in Japan 2004; 35(13): 43–51. DOI: https://doi.org/10.1002/scj.10342
Kouda N, Matsui N, Nishimura H et al. An examination of qubit neural network in controlling an inverted pendulum. Neural Processing Letters 2005; 22(3): 277–290. DOI: https://doi.org/10.1007/s11063-005-8337-2
Aytekin C, Kiranyaz S and Gabbouj M. Quantum mechanics in computer vision: Automatic object extraction. In Proc. ICIP 2013. pp. 2489–2493. DOI: https://doi.org/10.1109/ICIP.2013.6738513
Ezhov AA. Pattern recognition with quantum neural networks. In Singh S, Murshed N and Kropatsch W (eds.) Advances in Pattern Recognition ICAPR 2001, volume 2013. Springer Berlin Heidelberg, 2001. pp. 60–71. DOI: https://doi.org/10.1007/3-540-44732-6_7
Chrisley R. Quantum learning, (eds. p. pylkknen and p. pylkk) “new directions in cognitive science”. In Proceedings of the international symposium, Saariselka. Lapland, Finland, Helsinki. Finnish Association of Artificial Intelligence, pp. 77–89.
Kak S. Quantum neural computing. Advances in Imaging and Electron Physics 1995; 94: 259–313. DOI: https://doi.org/10.1016/S1076-5670(08)70147-2
Menneer T and Narayanan A. Quantum-inspired neural networks. Technical Report technical report R329, Department of Computer Science, University of Exeter, Exeter, United Kingdom, 1995.
Behrman EC, Niemel J, Steck JE et al. A quantum dot neural network. IEEE Transactions on Neural Networks 1996; .
Menneer T. Quantum Artificial Neural Networks. PhD Thesis, The University of Exeter, UK, 1998.
Ventura D and Martinez T. Quantum associative memory. IEEE Transactions on Neural Networks 1998; .
Weigang L. A study of parallel self-organizing map, 1998. E-print: http://xxx. lanl.gov/quantph/9808025.
Hirsh H. A quantum leap for ai. IEEE Intelligent System 1999; : 9.
Hogg T. Quantum search heuristics. IEEE Intelligent System 1999; : 12–14.
Kak S. Quantum computing and ai. IEEE Intelligent System 1999; : 9–11.
Ventura D. Quantum computational intelligence: Answers and questions. IEEE Intelligent System 1999; : 14–16.
Perus M. Mind: neural computing plus quantum consciousness. In Gams M, Paprzychi M and Wu X (eds.) Mind Versus Computer. IOS press, 1997. pp. 156–170.
Perus M. Common mathematical foundations of neural and quantum informatics. Zeitschrift Fur Angewandte Mathematik und Mechanik 1998; 78(1): 23–26.
Lagaris IE, Likas A and Fotiadis DI. Artificial neural network methods in quantum mechanics. ComputPhys Commun 1997; 104: 1–14. DOI: https://doi.org/10.1016/S0010-4655(97)00054-4
Vlasov AY. Quantum computations and images recognition, 1997. E-print: http://xxx.lanl.gov/quant-ph/ 9703010.
Perus M. Neural networks as a basis for quantum associate networks. Neural Network World 2000; 10(6): 1001–1013.
Perus M and Dey. Quantum system can realize content addressable associative memory. Applied Mathematics Letters 2000; 13(8): 31–36. DOI: https://doi.org/10.1016/S0893-9659(00)00092-6
Hu ZZ. Quantum computation via Neural Networks applied to Image processing and pattern recognition. PhD Thesis, University of Western Sydney, Australia.
Ventura D and Martinez T. An artificial neuron with quantum mechanical properties. In Proc. Intl.Conf. Artificial Neural Networks and Genetic Algorithms. pp. 482–485. DOI: https://doi.org/10.1007/978-3-7091-6492-1_106
Bhattacharyya S, Pal P and Bhowmik S. A quantum multilayer self organizing neural network for object extraction from a noisy background. In Proc. Fourth International Conference on Communication Systems and Network Technologies. pp. 512–518. DOI: https://doi.org/10.1109/CSNT.2014.108
Bhattacharjee S, Bhattacharyya S and Mondal NK. Quantum backpropagation neural network approach for modeling of phenol adsorption from aqueous solution by orange peel ash. In Bhattacharyya S and Dutta P (eds.) Handbook of Research on Computational Intelligence for Engineering, Science and Business. 2012. pp. 649–671. DOI: https://doi.org/10.4018/978-1-4666-2518-1.ch025
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Siddhartha Bhattacharyya, Pankaj Pal, Sandip Bhowmick
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
