Fast two-step segmentation of natural color scenes using hierarchical region-growing and a color-gradient network

Abstract

We present evaluation results with focus on combined image and efficiency performance of the Gradient Network Method to segment color images, especially images showing outdoor scenes. A brief review of the techniques, Gradient Network Method and Color Structure Code, is also presented. Different region-growing segmentation results are compared against ground truth images using segmentation evaluation indices Rand and Bipartite Graph Matching. These results are also confronted with other well established segmentation methods (EDISON and JSEG). Our preliminary results show reasonable performance in comparison to several state-of-art segmentation techniques, while also showing very promising results comparatively in the terms of efficiency, indicating the applicability of our solution to real time problems.

Improving Graph-Based Image Segmentation Using Nonlinear Color Similarity Metrics

“…Graph-based image segmentation methods, [1][2][3][4] where a graph of image segments is traversed in order to join similar segments, have been used in the last decades for low level image processing tasks. Even if some of these approaches employ additional discriminating heuristics when merging regions, 3 the core color discriminating function employed has still been a linear metric defined in some color space such as RGB, HSV/HSI or CIELab.…”