Abstract
We apply the Hyper-Conic Artificial Multilayer Perceptron (HC-MLP) to color image segmentation, where we consider image segmentation as a classification problem distinguishing between foreground and background pixels. The HC-MLP was designed by using the conic space and conformal geometric algebra. The neurons in the hidden layer contain a transfer function that defines a quadratic surface (spheres, ellipsoids, paraboloids and hyperboloids) by means of inner and outer products, and the neurons in the output layer contain a transfer function that decides whether a point is inside or outside a sphere. The Particle Swarm Optimization algorithm (PSO) is used to train the HC-MLP. A benchmark of fifty images is used to evaluate the performance of the algorithm and compare our proposal against statistical methods which use copula gaussian functions.
Chapter PDF
Similar content being viewed by others
References
Cheng, H.-D., Jiang, X.H., Sun, Y., Wang, J.: Color image segmentation: advances and prospects. Pattern Recognition 34(12), 2259–2281 (2001)
Salinas-Gutiérrez, R., Hernández-Aguirre, A., Rivera-Meraz, M.J.J., Villa-Diharce, E.R.: Supervised Probabilistic Classification Based on Gaussian Copulas. In: Sidorov, G., Hernández Aguirre, A., Reyes García, C.A. (eds.) MICAI 2010, Part II. LNCS, vol. 6438, pp. 104–115. Springer, Heidelberg (2010)
Szeliski, R.: Computer vision: algorithms and applications, pp. 235–269. Springer (2011)
Hernandez-Lopez, F.J., Rivera, M.: Binary segmentation of video sequences in real time. In: MICAI, pp. 163–168. IEEE Proceedings (2010)
Hernandez-Lopez, F.J., Rivera, M.: Change detection by probabilistic segmentation from monocular view. In: Machine Vision and Applications (2012) (to appear)
Serrano Rubio, J.P., Hernández Aguirre, A., Herrera Guzmán, R.: A Conic Higher Order Neuron Based on Geometric Algebra and Its Implementation. In: Batyrshin, I., Mendoza, M.G. (eds.) MICAI 2012, Part II. LNCS, vol. 7630, pp. 223–235. Springer, Heidelberg (2013)
Lescure, P., Meas-Yedid, V., Dupoisot, H., Stamon, G.: Color segmentation on biological microscope images. In: Proceeding of SPIE, Application of Artificial Neural Networks in Image Processing IV, San Jose, California, January 28-29, pp. 182–193 (1999)
Rae, R., Ritter, H.J.: Recognition of human head orientation based on artificial neural networks. IEEE Trans. Neural Network 9(2), 257–265 (1998)
Fang, Y., Pan, C., Liu, L.: On-line training of neural network for color image segmentation. In: Wang, L., Chen, K., S. Ong, Y. (eds.) ICNC 2005. LNCS, vol. 3611, pp. 135–138. Springer, Heidelberg (2005)
Perwass, C., Banarer, V., Sommer, G.: Spherical decision surfaces using conformal modelling. In: Michaelis, B., Krell, G. (eds.) DAGM 2003. LNCS, vol. 2781, pp. 9–16. Springer, Heidelberg (2003)
Dorst, L., Fontijne, D., Mann, S.: Geometric Algebra for Computer Science: An Object-Oriented Approach to Geometry. The Morgan Kaufmann Series in Computer Graphics, pp. 23–57, 355–389. Morgan Kaufmann Publishers Inc., San Francisco (2007)
Engelbrecht Andries, P.: Fundamental of Computational Swarm Intelligence. Wiley (2005)
Van den Bergh, F., Engelbrecht, A.P.: A study of particle swarm optimization particle trajectories. Information Sciences 176(8), 937–971 (2006)
Blake, A., Rother, C., Brown, M., Perez, P., Torr, P.: Interactive image segmentation using an adaptive GMMRF model. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 428–441. Springer, Heidelberg (2004)
Rother, C., Kolmogorov, V., Blake, A., Brown, M.: Image and video editing, http://research.microsoft.com/en-us/um/cambridge/projects/visionimagevideoediting/segmentation/grabcut.htm
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Serrano, J.P., Hernández, A., Herrera, R. (2014). Color Image Segmentation with a Hyper-Conic Multilayer Perceptron. In: Klette, R., Rivera, M., Satoh, S. (eds) Image and Video Technology. PSIVT 2013. Lecture Notes in Computer Science, vol 8333. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-53842-1_31
Download citation
DOI: https://doi.org/10.1007/978-3-642-53842-1_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-53841-4
Online ISBN: 978-3-642-53842-1
eBook Packages: Computer ScienceComputer Science (R0)