A Method of Multi-Pattern Classification with Encoded Feature-MasksA Multiple Networks Fusion Approach for 3-D Ojbect Recognition from 2-D Veiws

[1] Francis T S, Jutamulia Y S. Optical Pattern Recognition. New York: Cambridge University Press, 1998.

[2] Kumar B V K V. Tutorial survey of composite filter designs for optical correlators. Appl. Opt., 1992, 31(23):4773～4800

[3] Mahalanobis A, Casasent D. Laser class iconic pattern recognition-an OCR case study. Proc. SPIE, 1986, 726:2～27

[5] Edelman S, Weinshall D. A self-organizing multiple-view representation of 3D objects. Biol. Cyber., 1991, 64(3):209～219

[6] Poggio T, Edelman S. A network that learns to recognize three-dimensional objects. Nature, 1990, 343(6255):263～266

[7] Poggio T, Girosi F. Regularization algorithms for learning that are equivalent to multilayer networks. Science, 1990, 247(4945):978～982

[9] Sadjadj F. Module networks approaches for automatic target recognition. Proc. SPIE, 1995, 2271:303～313

[10] Cho S B, Kim J H. Multiple neural networks fusion using fuzzy integral. IEEE Trans. Neural Network, 1995, 5(4):380～384

[11] Wang Linchen, Der S Z, Nasrabadi N Z. Composite classifiers for automatic target recognition. Opt. Engng., 1998, 37(3):858～868