The Objective Evaluation of Image Object Segmentation Quality

Abstract

In this paper, a novel objective quality metric is proposed for individual object segmentation in images. We analyze four types of segmentation errors, and verify experimentally that besides quantity, area and contour, the distortion of object content is another useful segmentation quality index. Our metric evaluates the similarity between ideal result and… (More)
DOI: 10.1007/978-3-319-02895-8_42

7 Figures and Tables

Topics

  • Presentations referencing similar topics