Recent Changes - Search:


edit SideBar


Ten Pros And Cons Against Performance Characterisation Of Vision Algorithms

W. Foerstner, Proceedings of ECCV Workshop on Performance Characteristics of Vision Algorithms, Cambridge, UK, April 1996.

Also in Machine Vision Applications, 9 (5/6), 1997, pp.215-218.

This paper has been written by someone who wants this field to be considered as a scientific discipline. It contains all the arguments necessary to explain to people why they need to take their research a little more seriously and put more effort into algorithm evaluation, if they want the subject to make progress. It is the kind of material which would be taught on an undergraduate course in computer vision, should one ever exist, in the hope that by the time students got to the point of doing research the attitudes needed would be firmly entrenched.

NAT 9/3/2005

Edit - History - Print - Recent Changes - Search
Page last modified on March 05, 2012, at 03:56 PM