Abstract
In this paper, a bio-inspired neural network is developed to represent images and analysis features of images effectively. This model adopts schemes of retinal ganglion cells (GC) working and GCs’ non-classical receptive fields (nCRF) that can dynamically adjust their sizes/scales according to the visual information. Extensive experiments are provided to value the effect of image representing, and experimental results show that this neural network model can represent images at a low cost and with a favor in improving both segmentation and integration processing. Most importantly, the GC-array model provides a basic infrastructure for image semantic extraction.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
McIlwain, J.T.: Some evidence concerning the physiological basis of the periphery effect in the cat’s retina. Exp. Brain Res. 1, 265–271 (1966)
Ikeda, H., Wright, M.J.: The outer disinhibitory surround of the retinal ganglion cell receptive field. The Journal of Physiology 226, 511 (1972)
Krüger, J., Fischer, B.: Strong periphery effect in cat retinal ganglion cells. Excitatory responses in ON-and OFF-center neurones to single grid displacements. Exp. Brain Res. 18, 316–318 (1973)
Feghali, J.G., Jin, J.C., Odom, J.V.: Effect of short-term intraocular pressure elevation on the rabbit electroretinogram. Invest. Ophth. Vis. Sci. 32, 2184–2189 (1991)
Shou, T., Wang, W., Yu, H.: Orientation biased extended surround of the receptive field of cat retinal ganglion cells. Neuroscience 98, 207–212 (2000)
Fauqueur, J., Boujemaa, N.: Region-based image retrieval: Fast coarse segmentation and fine color description. Journal of Visual Languages & Computing 15, 69–95 (2004)
Deng, Y., Manjunath, B.S., Kenney, C., Moore, M.S., Shin, H.: An efficient color representation for image retrieval. IEEE Transactions on Image Processing 10, 140–147 (2001)
Saykol, E., Gudukbay, U., Ulusoy, O.: A histogram-based approach for object-based query-by-shape-and-color in image and video databases. Image Vision Comput. 23, 1170–1180 (2005)
Chaoyi, Q.F.L.: Mathematical Simulation of Disinhibitory Properties of Concentric Receptive Field. Acta Biophysica Sinica 11, 214–220 (1995)
Xianglin, Q., Xiaochuan, P., Yunjiu, W.: A mathematical model of integration field beyond receptive field of cortical neuron. In: Proceedings of the 9th International Conference on Neural Information Processing, ICONIP 2002, vol. 4, pp. 1694–1698 (2002)
Ghosh, K., Sarkar, S., Bhaumik, K.: A possible mechanism of zero-crossing detection using the concept of the extended classical receptive field of retinal ganglion cells. Biol. Cybern. 93, 1–5 (2005)
Ghosh, K., Sarkar, S., Bhaumik, K.: A possible explanation of the low-level brightness–contrast illusions in the light of an extended classical receptive field model of retinal ganglion cells. Biol. Cybern. 94, 89–96 (2006)
Hayashi, I., Maeda, T.: Structure Evaluation of Receptive Field Layer in TAM Network, vol. 2, pp. 1541–1547. IEEE (2006)
Kenyon, G.T., Travis, B.J., Theiler, J., George, J.S., Stephens, G.J., Marshak, D.W.: Stimulus-specific oscillations in a retinal model. IEEE Transactions on Neural Networks 15, 1083–1091 (2004)
Perrinet, L., Samuelides, M., Thorpe, S.: Coding static natural images using spiking event times: do neurons cooperate? IEEE Transactions on Neural Networks 15, 1164–1175 (2004)
Wei, H., Zuo, Q., Lang, B.: Multi-scale image analysis based on non-classical receptive field mechanism. In: Lu, B.-L., Zhang, L., Kwok, J. (eds.) ICONIP 2011, Part III. LNCS, vol. 7064, pp. 601–610. Springer, Heidelberg (2011)
Wei, H., Lang, B., Zuo, Q.: Contour detection model with multi-scale integration based on non-classical receptive field. Neurocomputing (2012)
Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 22, 888–905 (2000)
Dahlhaus, E., Johnson, D.S., Papadimitriou, C.H., Seymour, P.D., Yannakakis, M.: The complexity of multiway cuts, pp. 241–251. ACM (1992)
Grigorescu, C., Petkov, N., Westenberg, M.A.: Contour detection based on nonclassical receptive field inhibition. IEEE T. Image Process 12, 729–739 (2003)
Elder, J.H.: Are edges incomplete? Int. J. Comput Vision 34, 97–122 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wei, H., Zuo, Q., Lang, B. (2013). A General Image Representation Scheme and Its Improvement for Image Analysis. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds) Artificial Neural Networks and Machine Learning – ICANN 2013. ICANN 2013. Lecture Notes in Computer Science, vol 8131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40728-4_45
Download citation
DOI: https://doi.org/10.1007/978-3-642-40728-4_45
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40727-7
Online ISBN: 978-3-642-40728-4
eBook Packages: Computer ScienceComputer Science (R0)