Image segmentation based on semi-greedy region merging

Region merging algorithms are known to be fast when the merge criteria are relatively loose but very slow when extended schemes are applied. However, since region merging is greedy and looks only at local information, it is susceptible to suboptimal merge pathways as well as to outliers. This paper presents a fast and effective region merging scheme using a semi-greedy merging criterion and an adaptive threshold (SGAT) to control segmentation resolution. In quantitative analysis on standard benchmarks data, the proposed method performs the best, with respect to specific metrics as well as overall, compared to other segmentation methods.