Edge Detection Using Integrate and Fire Neuron

Yıl 2019, Cilt: 23 Sayı: 2, 611 - 616, 25.08.2019

Mürsel Ozan İncetaş , Rukiye Uzun Arslan

https://doi.org/10.19113/sdufenbed.570597

Cited By: 1

Öz

Edge
detection is one of the most basic stages of image processing and have been
used in many areas. Its purpose is to determine the pixels formed the objects.
Many researchers have aimed to determine objects' edges correctly, like as they
are determined by the human eye. In this study, a new edge detection technique
based on spiking neural network is proposed. The proposed model has a different
receptor structure than the ones found in literature and also does not use gray
level values of the pixels in the receptive field directly. Instead, it takes
the gray level differences between the pixel in the center of the receptive
field and others as input. The model is tested by using BSDS train dataset.
Besides, the obtained results are compared with the results calculated by Canny
edge detection method.  

Anahtar Kelimeler

Edge detection, Receptive field, Spiking neuronal network

Topla ve Ateşle Nöron Modeli Kullanılarak Kenar Algılama

Öz

Kenar
algılama, görüntü işlemenin en temel aşamalarından biridir ve birçok farklı
alanda kullanılmaktadır. Kenar belirleme yöntemlerinin amacı görüntüyü
oluşturan pikselleri belirlemektir. Çoğu araştırmacı, insan gözünün belirlediği
gibi nesnelerin kenarlarını doğru algılamayı hedeflemiştir. Bu çalışmada,
iğnecikli sinir ağ yapısına dayalı yeni bir kenar algılama tekniği
önerilmiştir. Önerilen model, literatürde bulunanlardan farklı bir alıcı
yapısına sahiptir ve doğrudan alıcı alandaki piksellerin gri seviye değerlerini
kullanmamaktadır. Bunun yerine, girdi olarak alıcı alanın ortasındaki piksel
ile diğerleri arasındaki gri seviye farklarını kullanarak kenar algılama
işlemini gerçekleştirmektedir. Geliştirilen model, BSDS öğrenme veri seti
kullanılarak test edilmiştir. Ayrıca, elde edilen sonuçlar Canny kenar algılama
yöntemi yardımıyla hesaplananlar ile karşılaştırılmıştır.

Anahtar Kelimeler

Kenar algılama, Alıcı bölge, İğnecikli sinir ağları

Kaynakça

• [1] Canny, J. A. 1986. Computational Approach to Edge-detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6), 679-698.
• [2] Demirci, R. 2007. Similarity Relation Matrix-Based Color Edge Detection. AEU-International Journal of Electronics and Communications, 61(7), 469-477.
• [3] Gonzalez, R.C., Woods, R.E. 2008. Digital Image Processing, 3rd Ed. Pearson/Prentice Hall, New Jersey.
• [4] Wandell, B. A. 1995. Foundations of Vision. Sinauer Associates, Inc., Sunderland, MA, 476s.
• [5] Kaiser, P. K., Boynton, R. 1996. Human Color Vision, 2nd edition. Optical Society of America, Washington, DC, 652s.
• [6] Nadenau, M. J., Winkler, S., Alleysson, D., Kunt, M. 2002. Human Vision Models for Perceptually Optimized Image Processing -- A Review. Proc. of the IEEE 32.
• [7] Kerr, D., Mcginnity, T.M., Coleman, S., Clogenson, M. 2015. A Biologically Inspired Spiking Model of Visual Processing for Image Feature Detection. Neurocomputing, 158, 268-280.
• [8] Kandel, E. R., Schwartz, J. H., Jessell, T. M. 2000. Principles of Neural Science. 4nd edition, McGraw-Hill, New York, 1760s.
• [9] Hosoya, T., Baccus, S. A., Meister, M. 2005. Dynamic Predictive Coding by the Retina. Nature, 436, 71 – 77.
• [10] Wu, O. X., McGinnity, T. M., Maguire, L. M., Belatreche, A., Glackin, B. 2007. Edge Detection Based On Spiking Neural Network Model. Huang, D. S, Heutte, L. and Loog, M. ed. Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence. ICIC 2007. Lecture Notes in Computer Science, Springer, Berlin, 4682, 26-34.
• [11] DiCarlo, J., Zoccolan, D., Rust, N.C. 2012. How does the Brain Solve Visual Object Recognition? Neuron 73(3), 415–434.
• [12] Clark, A., Tyler, L. K. 2015. Understanding What We See: How We Derive Meaning from Vision. Trends Cogn. Sci. 19(11), 677–687.
• [13] Ghahari, A., Enderle, J. D. 2015 Models of Horizontal Eye Movements: Part4, A Multiscale Neuron and Muscle Fiber-Based Linear Saccade Model. Synthesis Lectures on Biomedical Engineering, Morgan & Claypool Publishers.
• [14] Kunkle, D. R., Merrigan, C. 2002. Pulsed Neural Networks and Their Application. Computer Science Dept., College of Computing and Information Sciences, Rochester Institute of Technology.
• [15] Ghosh, D. S., Adeli, H. 2009. Spiking neural networks. Int. J. Neural Syst. 19(4), 295-308.
• [16] Ponulak, F., Kasinski, A. 2011. Introduction to Spiking Neural Networks: Information Processing, Learning and Applications. Acta Neurobiol. Exp., 71(4), 409-433. [17] Rozenberg, G., Bäck, T., Kok, J. N. 2011. Handbook of Natural Computing. Springer, Berlin, 2052s.
• [17] Rozenberg, G., Bäck, T., Kok, J. N. 2011. Handbook of Natural Computing. Springer, Berlin, 2052s.
• [18] Yedjour, H., Meftah, B., Le´zoray, O., Benyettou, A. 2017. Edge Detection Based on Hodgkin–Huxley Neuron Model Simulation. Cogn. Process., 18, 315–323.
• [19] Wu, Q. X., McGinnity, T. M., Maguire, L. P., Glackin, B., Belatreche, A. (2006). Learning Mechanism in Networks of Spiking Neurons. Studies in Computational Intelligence. Springer-Verlag, 35, 171–197.
• [20] Meftah, B., Lezoray, O. & Benyettou, A. (2010) Segmentation and Edge Detection Based on Spiking Neural Network Model. Neural Process Lett., 32(2), 131–146.
• [21] Kerr, D., Coleman, S., McGinnity, M., Wu, Q. X., Clogenson, M. 2011. Biologically Inspired Edge Detection. 11th International Conference on Intelligent Systems Design and Applications, 22-24 November, Cordoba, Spain.
• [22] Diaz-Pernas, F. J., Anton-Rodriguez, M., Torre-Diez, I., Martinez-Zarzuela, M., Gonzalez-Ortega, D., Boto-Giralda, D., Diez-Higuera, J. F. 2011. Surround Suppression and Recurrent Interactions V1–V2 for Natural Scene Boundary Detection. Image segmentation. ss 99–118. Ho P-G Eds.2011. INTECH Publisher.
• [23] Azzopardi, G., Petkov, N. 2012. A CORF Computational Model of a Simple Cell that Relies on LGN Input Outperforms the Gabor Function Model. Biol Cybern., 106(3), 177–189.
• [24] Hodgkin, A., Huxley, A. 1952. A Quantitative Description of Membrane Current and Its Application to Conduction and Excitation in Nerve. J Physiol., 117, 500-544.
• [25] Nelson, M. E. Electrophysiological Models. 2004. Data Basing the Brain: From Data To Knowledge. Koslow, S., Subramaniam, S., eds. Wiley, New York, 480s.
• [26] FitzHugh, R. 1969. Mathematical Models of Excitation and Propagation in Nerve. McGraw Hill, New York.
• [27] Nagumo, J., Sato, S. 1972. On a Response Characteristic of Mathematical Neuron Model. Kybernetik, 10(3), 155-164.
• [28] Gerstner, W., Kistler, W. M. 2002. Spiking Neuron Models: Single Neurons, Populations, Plasticity. Cambridge Univ. Press, United Kingdom, 496s.
• [29] Izhikevich, E. M. 2003. Simple Model of Spiking Neurons. IEEE Trans. Neural Networks, 14, 1569–1572.
• [30] Maass, W., Bishop, C. M. 1999. Pulsed Neural Networks. MIT Press, Cambridge, MA, 377s.
• [31] Richardson, M. J. E., Gerstner, W. 2003. Conductance Versus Current-Based Integrate-and-Fire Neurons: Is There Qualitatively New Behaviour?.
• [32] Mainen, Z. F. 1995. Mechanisms of spike generation in neocortical neurons. University of California, Doctoral dissertation, 72s, San Diego.
• [33] Destexhe, A. 1997. Conductance-based integrate-and-fire models. Neural Comput., 9, 503-514.
• [34] Koch, C. 1999. Biophysics of Computation: Information Processing in Single Neurons. Oxford University Press, New York, 588s.
• [35] Dayan, P., Abbott, L. F. 2001. Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems. The MIT Press, Cambridge, 480s.
• [36] Müller, E. 2003. Simulation of high-conductance states in cortical neural networks. University of Heidelberg, Master’s Thesis, Germany, 41s.