A HOUGH TRANSFORM SYSTEM BASED ON NEURAL NETWORKS

被引：11

作者：

DEMPSEY, GL

MCVEY, ES

机构：

[1] Department of Electrical Engineering, Bradley University, Peoria

[2] Department of Electrical Engineering, University of Virginia, Charlottesville, VA

来源：

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS | 1992年 / 39卷 / 06期

关键词：

Analog circuitry - Hough transform system - Image to parameter space mapping;

D O I：

10.1109/41.170971

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Identification of lines is a basic machine vision problem that is essential in a large number of applications. The Hough transform is ideal for line detection because it is robust, relatively insensitive to noise, and degrades gracefully to occlusions in addition to other advantages. But it has the disadvantage of being computationally intensive, which makes it relatively slow, and for this reason it has found little use in real-time applications where its unique abilities would allow it to have wide utility. This handicap could be removed if practical implementation with artificial neural networks were possible. Neural-like analog circuitry is suggested for the image to parameter space mapping, and a modified Hopfield optimization network is proposed for the parameter space peak detection. Solution time under 50 mus is obtainable with general purpose operational amplifiers. Example system applications include autonomous navigation, tracking multiple targets, curve following, mensuration, and image recognition.

引用

页码：522 / 528

页数：7

共 22 条

[1]

Illingworth J., Kittler J., A survey of the Hough transform, Computer Vision, Graphics and Image Processing, 44, pp. 87-116, (1988)

[2]

Inigo R.M., McVey E.S., Berger B.J., Wirtz M.J., Machine vision applied to vehicle guidance, IEEE Trans. Pattern Anal. Machine Intell., PAMI-6, 6, pp. 820-826, (1984)

[3]

McVey E.S., Dempsey G.L., Garcia J., Inigo R.M., Artificial neural network implementation of the Hough transform, Proc. 23rd Asilomar Conf Signals, Syst. Comput, 1, pp. 128-132, (1989)

[4]

Dempsey G.L., Neural network implementation of the Hough transform, Ph.D. dissertation, (1991)

[5]

Hough P.V.C., A method and means for recognizing complex patterns, U.S. Patent 3,609,654, (1962)

[6]

Rhodes F.M., Dituri J.J., Chapman G.H., Emerson B.E., Soares A.M., Raffel J.I., A monolithic Hough transform processor based on restructurable VLSI, IEEE Trans. Pattern Anal. Machine Intell., PAMI-10, 1, pp. 106-110, (1988)

[7]

Hanahara K., Maruyama T., Uchiyama T., A real-time processor for the Hough transform, IEEE Trans. Pattern Anal. Machine Intell., PAMI-10, 1, pp. 121-125, (1988)

[8]

O'Gorman L., Sanderson A.C., The converging squares algorithm: An efficient method for locating peaks in multidimensions, IEEE Trans. Pattern Anal. Machine Intell., PAMI-6, pp. 280-288, (1984)

[9]

Eklundh J.O., Rosenfield A., Peak detection using difference operators, IEEE Transactions on Pattern Anal. Machine Intell., PAMI-1, pp. 317-325, (1979)

[10]

Feldman J.A., Ballard D.H., Connectionist models and their properties, Cognitive Sci., 6, pp. 205-254, (1982)

← 1 2 3 →