Talk:Feature detection (computer vision)

Latest comment: 7 years ago by JS Hoyer in topic Bad external link


Possible Infobox edit

I have created an infobox for all pages related to corner/edge/blob/feature/interest point detection: User:Keeganmann/Corner Detection Navagation.

Should I add it and is it a good idea? Keeganmann (talk) 00:38, 17 February 2008 (UTC)Reply

I have looked at the infobox that you created. It contains some information that may be informative. However, it unfortunately has a strong bias towards certain parts of the information in the feature detection pages (edge detection, corner detection, blob detection, ridge detection). In particular it gives overemphasis to the Harris affine and Hessian affine detectors while omitting other well-known feture detectors, such as the regular Harris operator and the Shi and Tomasi corner detector. In particular, the notion of ridge detection is missing. If an information box should be created, it has to be more balanced with regard to the technical contents. The information in the table of feature detectors in the page Feature detection (computer vision) is more balanced in this regard. Concerning the last item "Miscellaneous" in table, it would be more informative to rename it into "Affine invariant feature detectors" and also put the Harris affine and Hessian affine detectors under such a header. Furthermore, the link to the Laplacian operator should also be moved to a link to the section on the Laplacian of Gaussian operator within the blob detection. Tpl (talk) 10:35, 18 February 2008 (UTC)Reply

The corner detection image is confusing, I can barely see the corners. Not a good image to use. Kegon (talk) 18:55, 19 July 2011 (UTC)Reply

Generalization needed edit

Feature detection applies to more than just computer vision. It also refers to speech processing techniques in which phonemes are encoded by their cepstrum (inverse spectrum). This article could use some expansion, so I'll try to get that done. SamuelRiv 13:22, 5 November 2007 (UTC)Reply

I do also have some concerns about the inclusion of this article in the Neuroethology project. As the article is written now, it deals with feature detection within the area of computer vision. Should we therefore move the current article to Feature detection (computer vision)? Tpl 15:33, 3 December 2007 (UTC)Reply

Translation into Chinese Wikipedia edit

The 07:41, 27 February 2008 Tpl version of this article is translated into Chinese Wikipedia--Philopp (talk) 10:40, 11 May 2008 (UTC)Reply

Bad link to CORF edit

The navbox on the right lists a link to CORF under edge detection, but the link is bad. It redirects through to a wiktionary entry which is totally irrelevant. I see in [[1]] that the algorithm has had some undesirable promotion within wikipedia, so maybe this is a relic of that as well? Regardless, it seems like it should be removed. Leopd (talk) 17:00, 1 October 2012 (UTC)Reply

I agree and will remove it. Tpl (talk) 14:58, 2 October 2012 (UTC)Reply


Bad external link edit

Domain lease expired or whatever. [2] JS Hoyer (talk) 14:55, 24 February 2017 (UTC)Reply