Extended probabilistic Rand index and the adjustable moving window-based pixel-pair sampling method
This work addresses incremental improvements in segmentation evaluation metrics for computer vision researchers.
The paper tackled the probabilistic Rand index's limited value range and unclear normalization by proposing an extended index that doubles the effective range and an adjustable pixel-pair sampling method, with experiments showing effective and efficient performance.
The probabilistic Rand (PR) index has the following three problems: It lacks variations in its value over images; the normalized probabilistic Rand (NPR) index to address this is theoretically unclear, and the sampling method of pixel-pairs was not proposed concretely. In this paper, we propose methods for solving these problems. First, we propose extended probabilistic Rand (EPR) index that considers not only similarity but also dissimilarity between segmentations. The EPR index provides twice as wide effective range as the PR index does. Second, we propose an adjustable moving window-based pixel-pair sampling (AWPS) method in which each pixel-pair is sampled adjustably by considering granularities of ground truth segmentations. Results of experiments show that the proposed methods work effectively and efficiently.