Abstract | ||
---|---|---|
It is frequently remarked that designers of computer vision algorithms and systems cannot reliably predict how algorithms will respond to new problems. A variety of reasons have been given for this situation and a variety of remedies prescribed in literature. Most of these involve, in some way, paying greater attention to the domain of the problem and to performing detailed empirical analysis. The goal of this paper is to review what we see as current best practices in these areas and also suggest refinements that may benefit the field of computer vision. A distinction is made between the historical emphasis on algorithmic novelty and the increasing importance of validation on particular data sets and problems. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1016/j.cviu.2007.04.006 | Computer Vision and Image Understanding |
Keywords | Field | DocType |
vision system design,performance evaluation,computer vision,computer vision algorithm,historical emphasis,performance characterization,new problem,performance assessment,detailed empirical analysis,increasing importance,algorithmic novelty,greater attention,particular data set,current best practice,component,face recognition algorithms,optical flow,object recognition,best practice,image registration,finite element methods,medical,principal,vision system,pattern recognition | Computer vision,Facial recognition system,Best practice,Algorithmics,Computer science,Computer vision algorithms,CONTRAST ENHANCED MRI,Artificial intelligence,Novelty,Optical flow,Machine learning,Cognitive neuroscience of visual object recognition | Journal |
Volume | Issue | ISSN |
109 | 3 | Computer Vision and Image Understanding |
Citations | PageRank | References |
31 | 1.17 | 163 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Neil A. Thacker | 1 | 517 | 72.16 |
Adrian F. Clark | 2 | 221 | 72.99 |
John L. Barron | 3 | 183 | 27.32 |
J. Ross Beveridge | 4 | 1716 | 190.52 |
Patrick Courtney | 5 | 31 | 1.17 |
William R Crum | 6 | 448 | 32.49 |
Visvanathan Ramesh | 7 | 2586 | 171.97 |
Christine Clark | 8 | 31 | 1.17 |