Abstract
Biological vision systems have become highly optimized over millions of years of evolution, developing complex neural structures to represent and process stimuli. Moreover, biological systems of vision are typically far more efficient than current human-made machine vision systems. The present report describes a non-task-dependent image representation schema that simulates the early phase of a biological neural vision mechanism. We designed a neural model involving multiple types of computational units to simulate ganglion cells and their non-classical receptive fields, local feedback control circuits and receptive field dynamic self-adjustment mechanisms in the retina. We found that, beyond the pixel level, our model was able to represent images self-adaptively and rapidly. In addition, the improved representation was found to substantially facilitate contour detection. We propose that this improvement arose because ganglion cells can resize their receptive fields, enabling multiscale analysis functionality, a neighborhood referring function and a localized synthesis function. The ganglion cell layer is the starting point of subsequent diverse visual processing. The universality of this cell type and its functional mechanisms suggests that it will be useful for designing image processing algorithms in future.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Papari, G., Petkov, N.: An improved model for surround suppression by steerable filters and multilevel inhibition with application to contour detection. Pattern Recogn. 44, 1999–2007 (2011)
Ghosh, K., Sarkar, S., Bhaumik, K.: Image enhancement by high-order Gaussian derivative filters simulating non-classical receptive fields in the human visual system. Pattern Recognition and Machine Intelligence, 453–458 (2005)
Ghosh, K., Sarkar, S., Bhaumik, K.: A bio-inspired model for multiscale representation of even order gaussian derivatives. In: Proceedings of the 2004 Intelligent Sensors, Sensor Net-works and Information Processing Conference, pp. 497–502 (2004)
Linde, O., Lindeberg, T.: Object recognition using composed receptive field histograms of higher dimensionality. In: Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, vol. 2, pp. 1–6 (2004)
Dacey, D.M.: The mosaic of midget ganglion cells in the human retina. The Journal of Neuroscience 13, 5334–5355 (1993)
Trexler, E.B., Li, W., Massey, S.C.: Simultaneous contribution of two rod pathways to AII amacrine and cone bipolar cell light responses. J. Neurophysiol. 93, 1476–1485 (2005)
Kolb, H., Nelson, R.: Off‐alpha and OFF‐beta ganglion cells in cat retina: II. Neural circuitry as revealed by electron microscopy of HRP stains. The Journal of Comparative Neurology 329, 85–110 (1993)
Sjöstrand, J., Olsson, V., Popovic, Z., Conradi, N.: Quantitative estimations of foveal and extra-foveal retinal circuitry in humans. Vision Res. 39, 2987–2998 (1999)
Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE T. Pattern Anal. 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)
Ren, X.F., Fowlkes, C.C., Malik, J.: Learning probabilistic models for contour completion in natural images. Int. J. Comput. Vision 77, 47–63 (2008)
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, Qs., Lang, B. (2013). A Retina-Inspired Neurocomputing Circuit for Image Representation. In: Rojas, I., Joya, G., Cabestany, J. (eds) Advances in Computational Intelligence. IWANN 2013. Lecture Notes in Computer Science, vol 7903. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38682-4_41
Download citation
DOI: https://doi.org/10.1007/978-3-642-38682-4_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38681-7
Online ISBN: 978-3-642-38682-4
eBook Packages: Computer ScienceComputer Science (R0)