Seeded Laplaican: An Eigenfunction Solution for Scribble Based Interactive Image Segmentation

TL;DR

This paper introduces a novel eigenfunction-based approach for scribble-based interactive image segmentation that reduces computational complexity while maintaining high accuracy, outperforming existing methods on diverse natural image datasets.

Contribution

The paper proposes a new eigenfunction approximation method for graph Laplacian eigenvectors in interactive segmentation, eliminating the need for expensive eigenvector computations.

Findings

Achieves better qualitative segmentation results than state-of-the-art methods.

Demonstrates robustness across various feature vectors and dataset types.

Reduces computational complexity using pivot pixels without sacrificing accuracy.

Abstract

In this paper, we cast the scribble-based interactive image segmentation as a semi-supervised learning problem. Our novel approach alleviates the need to solve an expensive generalized eigenvector problem by approximating the eigenvectors using efficiently computed eigenfunctions. The smoothness operator defined on feature densities at the limit n tends to infinity recovers the exact eigenvectors of the graph Laplacian, where n is the number of nodes in the graph. To further reduce the computational complexity without scarifying our accuracy, we select pivots pixels from user annotations. In our experiments, we evaluate our approach using both human scribble and "robot user" annotations to guide the foreground/background segmentation. We developed a new unbiased collection of five annotated images datasets to standardize the evaluation procedure for any scribble-based segmentation method. We experimented with several variations, including different feature vectors, pivot count and the number of eigenvectors. Experiments are carried out on datasets that contain a wide variety of natural images. We achieve better qualitative and quantitative results compared to state-of-the-art interactive segmentation algorithms.