In this paper, we propose the use of visible color difference in a new quantitative evaluation scheme for color image segmentation. With visible color difference, two measurements, named intra-region visual error and inter-region visual error, are defined to evaluate the quality of segmentation results. To fit for human's visual perception, segmentation results with an excessive amount of intra-region error are regarded as under-segmeritation, while segmentation results with too many inter-region errors are regarded as over-segmentation. Based on these two measurements, a complete scheme for the evaluation of color image segmentation is proposed. The simulation results demonstrate that this new scheme may provide a reliable and efficient way to automatically select the parameter settings for a given segmentation algorithm and to compare the performance between various segmentation algorithms.
|Journal||ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings|
|State||Published - 28 Sep 2004|
|Event||Proceedings - IEEE International Conference on Acoustics, Speech, and Signal Processing - Montreal, Que, Canada|
Duration: 17 May 2004 → 21 May 2004