Objective evaluation of video segmentation quality

• Published in: IEEE transactions on image processing Vol. 12; no. 2; pp. 186 - 200
• Main Authors: Correia, P.L., Pereira, F.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.02.2003; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adequacy; Adjustment; Algorithms; Applied sciences; Content based retrieval; Exact sciences and technology; Image processing; Image segmentation; Information, signal and communications theory; ISO standards; Layout; MPEG 4 Standard; MPEG 7 Standard; Object recognition; Object segmentation; Optimization; Partitioning algorithms; Recognition; Segmentation; Signal processing; Standards development; Telecommunications and information theory; Testing; Performance evaluation; Image quality; Image segmentation; Methodology; Objective analysis; Metric; Objective segmentation quality; video segmentation; segmentation quality evaluation; Video signal processing
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2002.807355

Video segmentation assumes a major role in the context of object-based coding and description applications. Evaluating the adequacy of a segmentation result for a given application is a requisite both to allow the appropriate selection of segmentation algorithms as well as to adjust their parameters for optimal performance. Subjective testing, the current practice for the evaluation of video segmentation quality, is an expensive and time-consuming process. Objective segmentation quality evaluation techniques can alternatively be used; however, it is recognized that, so far, much less research effort has been devoted to this subject than to the development of segmentation algorithms. This paper discusses the problem of video segmentation quality evaluation, proposing evaluation methodologies and objective segmentation quality metrics for individual objects as well as for complete segmentation partitions. Both standalone and relative evaluation metrics are developed to cover the cases for which a reference segmentation is missing or available for comparison.