Sub-Pixel Edge Detection on the Product Line

Article Preview

Abstract:

In this paper, we present a new method to detect sub-pixel edges of shape-known objects. Differ from other sub-pixel edge detection methods based on normal information, we use tangential information. We introduce theories of this method, as well as the influences on the performance of this method caused by size, sampling location and direction of the object. This new method has been practically applied and compared with other methods in real pictures on the product line. Results show that this method provides more accurate sub-pixel edge in practical applications.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

2526-2529

Citation:

Online since:

September 2013

Authors:

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Canny J. A computational approach to edge detection . IEEE Trans Pattern Analysis and Machine Intelligence1986; 8(6): 679–714.

Google Scholar

[2] Harris C, Stephens M. A combined corner and edge detector. In: Proc. 4th Proc. Alvey Vision Conf. Manchester, England, 1998; p.147–51.

Google Scholar

[3] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors. IEEE Trans Pattern Analysis and Machine Intelligence 2005; 27(10): 1615–30.

DOI: 10.1109/tpami.2005.188

Google Scholar

[4] A. Cumani, Edge detection in multispectral images, CVGIP: Graph Models Image Process, vol. 53, no. 1, p.40–51, Jan. (1991).

DOI: 10.1016/1049-9652(91)90018-f

Google Scholar

[5] S. K. Naik and C. A. Murthy, Standardization of Edge Magnitude in Color Images, IEEE Trans. Image processing, vol. 15, no. 9, Sept. (2006).

DOI: 10.1109/tip.2006.877408

Google Scholar