Performance Evaluation Tools for Zone Segmentation and Classification (PETS)

This paper overviews a set of Performance Evaluation ToolS (PETS) for zone segmentation and classification. The tools allow researchers and developers to evaluate, optimize and compare their algorithms by providing a variety of quantitative performance metrics. The evaluation of segmentation quality is based on the pixel-based overlaps between two sets of regions proposed by Randriamasy and Vincent [12]. PETS extends the approach by providing a set of metrics for overlap analysis, RLE and polygonal representation of regions and introduces type-matching to evaluate zone classification. The software is available for research use.

• Type: Conference
• Year: 2010
• Where: ICPR
• Authors: Wontaek Seo, Mudit Agrawal, David Doermann
• Keywords: Computer Vision, ICPR 2010