PSSI-MaxST: An Efficient Pixel-Segment Similarity Index Using Intensity and Smoothness Features for Maximum Spanning Tree Based Segmentation
Kaustubh Shivshankar Shejole, Gaurav Mishra
TL;DR
The paper addresses the inefficiency and seed-sensitivity of interactive graph-based segmentation when foreground and background share appearance. It introduces PSSI-MaxST, combining a Pixel Segment Similarity Index (PSSI) with MeanShift pre-segmentation and Maximum Spanning Tree partitioning to jointly capture color, texture, and smoothness while maintaining computational efficiency. The approach demonstrates superior segmentation quality (IoU/F1) and lower mean error on Image250 and GrabCut datasets, with competitive runtimes and robustness to marker initialization. The work contributes a linearly scalable similarity measure, a globally informed MaxST-based partitioning strategy, and public code, offering practical benefits for precise, user-guided segmentation tasks.
Abstract
Interactive graph-based segmentation methods partition an image into foreground and background regions with the aid of user inputs. However, existing approaches often suffer from high computational costs, sensitivity to user interactions, and degraded performance when the foreground and background share similar color distributions. A key factor influencing segmentation performance is the similarity measure used for assigning edge weights in the graph. To address these challenges, we propose a novel Pixel Segment Similarity Index (PSSI), which leverages the harmonic mean of inter-channel similarities by incorporating both pixel intensity and spatial smoothness features. The harmonic mean effectively penalizes dissimilarities in any individual channel, enhancing robustness. The computational complexity of PSSI is $\mathcal{O}(B)$, where $B$ denotes the number of histogram bins. Our segmentation framework begins with low-level segmentation using MeanShift, which effectively captures color, texture, and segment shape. Based on the resulting pixel segments, we construct a pixel-segment graph with edge weights determined by PSSI. For partitioning, we employ the Maximum Spanning Tree (MaxST), which captures strongly connected local neighborhoods beneficial for precise segmentation. The integration of the proposed PSSI, MeanShift, and MaxST allows our method to jointly capture color similarity, smoothness, texture, shape, and strong local connectivity. Experimental evaluations on the GrabCut and Images250 datasets demonstrate that our method consistently outperforms current graph-based interactive segmentation methods such as AMOE, OneCut, and SSNCut in terms of segmentation quality, as measured by Jaccard Index (IoU), $F_1$ score, execution time and Mean Error (ME). Code is publicly available at: https://github.com/KaustubhShejole/PSSI-MaxST.