Neuromorphic Methods for Recognition of Compact Image Objects

The issue of the recognition of tree species from high resolution aerial images is addressed in this paper. An approach based on the use of neural networks is presented and discussed in more detail. The networks perform classi cation and recognition operations on compact image objects, obtained by applying di erent tree isolation procedures. The recognition capabilities of two classes of networks, multilayer feedforward networks and holographic networks, are compared and some results of the research carried out in Austria and Canada, using aerial photographs and multispectral scanner images, are given. 1 Univ. du Qu ebec a Hull, Dept. d'Informatique, Canada 2 Petawawa National Forestry Institute, Ontario, Canada

[1]  Horst Bischof,et al.  Invariance problem for hierarchical neural networks , 1992, Optics & Photonics.

[2]  Axel Pinz,et al.  Information fusion in image understanding: LANDSAT classification and ocular fundus images , 1992, Other Conferences.

[3]  A. Pinz,et al.  Information fusion in image understanding , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.

[4]  Horst Bischof,et al.  Neural Network "Surgery": Transplantation of Hidden Units , 1992, ECAI.

[5]  Horst Bischof,et al.  Neural networks in image pyramids , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[6]  Axel Pinz,et al.  A computer vision system for the recognition of trees in aerial photographs , 1991 .

[7]  Bruce W. Suter,et al.  The multilayer perceptron as an approximation to a Bayes optimal discriminant function , 1990, IEEE Trans. Neural Networks.

[8]  Horst Bischof,et al.  Verwendung von neuralen Netzwerken zur Klassifikation natürlicher Objekte am Beispiel der Baumerkennung aus Farb-Infrarot-Luftbildern , 1990, ÖGAI.

[9]  John K. Tsotsos.  Analyzing vision at the complexity level , 1990, Behavioral and Brain Sciences.

[10]  Michael T. Manry,et al.  Iterative improvement of a Gaussian classifier , 1990, Neural Networks.

[11]  Horst Bischof,et al.  Constructing a neural network for the interpretation of the species of trees in aerial photographs , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[12]  M. W. Roth.  Survey of neural network technology for automatic target recognition , 1990, IEEE Trans. Neural Networks.

[13]  A. Pinz.  Wissensbasierte Informationsverarbeitung in der österreichischen Waldzustandsinventur , 1990 .

[14]  Geoffrey E. Hinton.  Connectionist Learning Procedures , 1989, Artif. Intell..

[15]  John Y. Aloimonos,et al.  Unification and integration of visual modules: an extension of the Marr Paradigm , 1989 .

[16]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[17]  Terrence J. Sejnowski,et al.  A Parallel Network that Learns to Play Backgammon , 1989, Artif. Intell..

[18]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[19]  T. Sejnowski,et al.  Predicting the secondary structure of globular proteins using neural network models. , 1988, Journal of molecular biology.

[20]  Terrence J. Sejnowski,et al.  Learned classification of sonar targets using a massively parallel network , 1988, IEEE Trans. Acoust. Speech Signal Process..

[21]  Terrence J. Sejnowski,et al.  NETtalk: a parallel network that learns to read aloud , 1988 .

[22]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[23]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[24]  M. Tills,et al.  Multi-detector electro-optical imaging scanner MEIS II. , 1984 .

[25]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[26]  W. E. Kock,et al.  Holography , 1971, Science.

[27]  I. G. BONNER CLAPPISON.  Editor , 1960, The Electric Power Engineering Handbook - Five Volume Set.