CVNov 21, 2016

The subset-matched Jaccard index for evaluation of Segmentation for Plant Images

arXiv:1611.06880v12 citations
Originality Synthesis-oriented
AI Analysis

This addresses the need for more accurate segmentation evaluation in plant image analysis, though it is incremental as it builds on existing Jaccard index methods.

The paper tackles the problem of evaluating region-level segmentation accuracy in plant images by introducing the subset-matched Jaccard index, which enforces a one-to-one mapping rule between regions in evaluated and ground truth images to improve assessment.

We describe a new measure for the evaluation of region level segmentation of objects, as applied to evaluating the accuracy of leaf-level segmentation of plant images. The proposed approach enforces the rule that a region (e.g. a leaf) in either the image being evaluated or the ground truth image evaluated against can be mapped to no more than one region in the other image. We call this measure the subset-matched Jaccard index.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes