An approach to edge detection based on the direction of edge elements

Abstract Hubel and Wiesel's results on the existence of special cortical cells responding to line segments of given orientation have motivated our study on the use of the direction of edge elements for a more effective local edge detection. The problems that justify a more sophisticated analysis are the discrimination of real from noisy intensity changes, as well as the reduction of the number of edge elements detected along real edges. A satisfactory solution to these two problems has been given by the development of a local operator, which after detecting an edge element which may belong to a real edge, uses an estimation of its direction in order to verify its existence in the middle of a systematic intensity change.

[1]  D Marr,et al.  Early processing of visual information. , 1976, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[2]  G. Granlund.  In search of a general picture processing operator , 1978 .

[3]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

[4]  D. Hubel,et al.  Anatomical demonstration of orientation columns in macaque monkey , 1978, The Journal of comparative neurology.

[5]  R A Kirsch,et al.  Computer determination of the constituent structure of biological images. , 1971, Computers and biomedical research, an international journal.

[6]  Edward S. Deutsch,et al.  A Quantitative Study of the Orientation Bias of Some Edge Detector Schemes , 1978, IEEE Transactions on Computers.

[7]  K. Ramesh Babu,et al.  Linear Feature Extraction and Description , 1979, IJCAI.