Neural Net Computing for Image Processing

Publisher Summary Artificial neural networks are an attempt to emulate the processing capabilities of biological neural systems. The basic idea is to realize systems capable of performing complex processing tasks by interconnecting a high number of very simple processing elements that might even work in parallel. They solve cumbersome and intractable problems by learning directly from data. An artificially neural network usually consists of a large amount of simple processing units, namely neurons, via mutual interconnection. It learns to solve problems by adequately adjusting the strength of the interconnections according to input data. It is easily adapted to new environments by learning. These features motivate extensive researches and developments in artificial neural networks. The main features of artificial neural networks are their massive parallel processing architectures and the capabilities of learning from the presented inputs. They can be utilized to perform a specific task only by means of adequately adjusting the connection weights, that is, by training them with the presented data. Learning is done in accordance with the direct comparison of the actual output of the network with known correct answers. It is also referred to as learning with a teacher. Neural networks have been successfully employed to solve a variety of computer vision problems. They are systems of interconnected simple processing elements. There exist many types of neural networks that solve a wide range of problems in the area of image processing.

[1]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[2]  A P Dhawan,et al.  Mammographic feature enhancement by computerized image processing. , 1988, Computer methods and programs in biomedicine.

[3]  José M. N. Leitão,et al.  Sequential and parallel image restoration: neural network implementations , 1994, IEEE Trans. Image Process..

[4]  John C. Platt.  A Resource-Allocating Network for Function Interpolation , 1991, Neural Computation.

[5]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[6]  Lawrence D. Jackel,et al.  Application of the ANNA neural network chip to high-speed character recognition , 1992, IEEE Trans. Neural Networks.

[7]  Anke Meyer-Bäse,et al.  Multiscale segmentation through a radial basis neural network , 1997, Proceedings of International Conference on Image Processing.

[8]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[9]  Sukhan Lee,et al.  A Gaussian potential function network with hierarchically self-organizing learning , 1991, Neural Networks.

[10]  Atam P. Dhawan,et al.  Analysis of mammographic microcalcifications using gray-level image structure features , 1996, IEEE Trans. Medical Imaging.

[11]  Huai Li,et al.  Artificial convolution neural network for medical image pattern recognition , 1995, Neural Networks.

[12]  Michael G. Strintzis,et al.  Nonlinear ultrasonic image processing based on signal-adaptive filters and self-organizing neural networks , 1994, IEEE Trans. Image Process..

[13]  Berkman Sahiner,et al.  Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images , 1996, IEEE Trans. Medical Imaging.

[14]  James D. Keeler,et al.  Layered Neural Networks with Gaussian Hidden Units as Universal Approximations , 1990, Neural Computation.

[15]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[16]  Josef Kittler,et al.  Floating search methods in feature selection , 1994, Pattern Recognit. Lett..

[17]  Thomas S. Huang,et al.  Image processing , 1971 .

[18]  Yi Sun,et al.  Improvement on performance of modified Hopfield neural network for image restoration , 1995, IEEE Trans. Image Process..

[19]  Erkki Oja,et al.  Self - Organizing Maps and Computer Vision , 1992 .

[20]  Jack Sklansky,et al.  A note on genetic algorithms for large-scale feature selection , 1989, Pattern Recognit. Lett..