On the optimality of image processing pipeline

✍ Scribed by Sameer Singh; Maneesha Singh

• Publisher: Elsevier Science
• Year: 2004
• Tongue: English
• Weight: 567 KB
• Volume: 37
• Category: Article
• ISSN: 0031-3203
• DOI: 10.1016/j.patcog.2003.08.005

✦ Synopsis

The optimisation of image processing steps such as segmentation and feature extraction individually in an application does not yield an optimal pipeline. In this paper we demonstrate how the use of di erent image segmentation algorithms directly impacts upon the quality of texture measures extracted from segmented regions and ÿnal classiÿcation ability. The di erence between the best and the worst possible performances by choosing di erent algorithms is found to be signiÿcant. We then develop the methodology for determining the optimal pipeline for scene analysis and show our experimental results on the publicly available benchmark "MINERVA".