Image Segmentation using Unsupervised Watershed Algorithm with an Over-segmentation Reduction Technique

TL;DR

This paper proposes an unsupervised watershed-based image segmentation method that reduces over-segmentation by leveraging color similarity between adjacent segments, improving segmentation quality.

Contribution

It introduces a novel over-segmentation reduction technique for watershed segmentation based on color distribution similarity between neighboring segments.

Findings

Improved segmentation accuracy over traditional watershed methods.

Effective reduction of over-segmentation in diverse images.

Demonstrated enhancement in segment coherence and object delineation.

Abstract

Image segmentation is the process of partitioning an image into meaningful segments. The meaning of the segments is subjective due to the definition of homogeneity is varied based on the users perspective hence the automation of the segmentation is challenging. Watershed is a popular segmentation technique which assumes topographic map in an image, with the brightness of each pixel representing its height, and finds the lines that run along the tops of ridges. The results from the algorithm typically suffer from over segmentation due to the lack of knowledge of the objects being classified. This paper presents an approach to reduce the over segmentation of watershed algorithm by assuming that the different adjacent segments of an object have similar color distribution. The approach demonstrates an improvement over conventional watershed algorithm.