Neutro-Connectedness Cut

TL;DR

This paper introduces Neutro-Connectedness Cut (NC-Cut), a novel interactive image segmentation method that combines pixel appearance and region topology to improve segmentation accuracy and robustness against initial ROI sensitivity.

Contribution

The work generalizes Neutro-Connectedness to be independent of object priors and proposes NC-Cut, a hybrid segmentation approach that overcomes limitations of existing methods.

Findings

Outperforms state-of-the-art methods on two datasets

Reduces sensitivity to initial ROI selection

Effectively excludes isolated background regions

Abstract

Interactive image segmentation is a challenging task and receives increasing attention recently; however, two major drawbacks exist in interactive segmentation approaches. First, the segmentation performance of ROI-based methods is sensitive to the initial ROI: different ROIs may produce results with great difference. Second, most seed-based methods need intense interactions, and are not applicable in many cases. In this work, we generalize the Neutro-Connectedness (NC) to be independent of top-down priors of objects and to model image topology with indeterminacy measurement on image regions, propose a novel method for determining object and background regions, which is applied to exclude isolated background regions and enforce label consistency, and put forward a hybrid interactive segmentation method, Neutro-Connectedness Cut (NC-Cut), which can overcome the above two problems by utilizing both pixel-wise appearance information and region-based NC properties. We evaluate the proposed NC-Cut by employing two image datasets (265 images), and demonstrate that the proposed approach outperforms state-of-the-art interactive image segmentation methods (Grabcut, MILCut, One-Cut, MGC_max^sum and pPBC).