A Feed-Forward Neural Network for Robust Segmentation of Color Images
A novel approach for segmentation of color images is proposed. The approach is based on a feed-forward neural network that learns to recognize the hue range of meaningful objects. Experimental results showed that the proposed method is effective and robust even in presence of changing environmental conditions. The described technique has been tested in the framework of the Robot Soccer World Cup Initiative (RoboCup). The approach is fully general and it may be successfully employed in any intermediate level image-processing task, where the color is a meaningful descriptor.
Unable to display preview. Download preview PDF.
- C. Amoroso and V. Morreale. Artificial vision for mobile robot. Technical report, CSAI Lab, Dept. of Electrical Engineering, Università di Palermo, 1999.Google Scholar
- R.C. Gonzalez and P. Wintz. Digital Image Processing, II ed. Addison-Wesley, 1987.Google Scholar
- H. Kitano, M. Asada, Y. Kuniyoshi, I. Noda, E. Osawa, and H. Matsubara. RoboCup: a challenge problem for AI. AI Magazine, 18(1):73–85, 1997.Google Scholar
- D. Nardi, G. Clemente, and E. Pagello. ART: azzurra robot team. Technical report, DIS Università di Roma “La Sapienza”, 1998.Google Scholar
- D.E. Rumelhart, G.E. Hinton, and R. Williams. Learning internal representation by error propagation. In D.E. Rumelhart and J.L. McClelland, editors, Parallel Distributed Processing, volume 1. MIT Press, Cambridge, MA, 1986.Google Scholar