A Hough transform system based on neural networks

Neural-like analog circuitry is suggested for image-to-parameter-space mapping, and a modified Hopfield optimization network is proposed for the parameter space peak detection. Solution time under 50 mu s is obtainable with general-purpose operational amplifiers. Example system applications include autonomous navigation, tracking multiple targets, curve following, mensuration, and image recognition. >

[1]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[2]  Rafael M. Inigo,et al.  Machine Vision Applied to Vehicle Guidance , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  G. L. Dempsey,et al.  An image processing resolution enhancement method for single-pixel targets , 1992, [1992] Conference Record of the Twenty-Sixth Asilomar Conference on Signals, Systems & Computers.

[4]  R.M. Inigo,et al.  Artificial neural network implementation of the hough transform , 1989, Twenty-Third Asilomar Conference on Signals, Systems and Computers, 1989..

[5]  Jerome A. Feldman,et al.  Connectionist Models and Their Properties , 1982, Cogn. Sci..

[6]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[7]  D Psaltis,et al.  Optical implementation of the Hopfield model. , 1985, Applied optics.

[8]  Lawrence O'Gorman,et al.  The Converging Squares Algorithm: An Efficient Method for Locating Peaks in Multidimensions , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[10]  E S. McVey,et al.  Artificial Neural Computer For Image Tracking , 1989, Photonics West - Lasers and Applications in Science and Engineering.

[11]  Yaser S. Abu-Mostafa,et al.  On the K-Winners-Take-All Network , 1988, NIPS.

[12]  G. L. Dempsey,et al.  Hough transform system enhancements resulting from neural network implementation , 1991, IEEE Proceedings of the SOUTHEASTCON '91.

[13]  Glenn H. Chapman,et al.  A Monolithic Hough Transform Processor Based on Restructurable VLSI , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  John Lazzaro,et al.  Winner-Take-All Networks of O(N) Complexity , 1988, NIPS.

[15]  Tsugito Maruyama,et al.  A Real-Time Processor for the Hough Transform , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Azriel Rosenfeld,et al.  Peak Detection Using Difference Operators , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Josef Kittler,et al.  A survey of the hough transform , 1988, Comput. Vis. Graph. Image Process..

[18]  Eugene S. McVey,et al.  A two-layer neural peak detector , 1991, [1991] Conference Record of the Twenty-Fifth Asilomar Conference on Signals, Systems & Computers.