A review of recent evaluation methods for image segmentation

An up-to-date review of the progress in the evaluation of image segmentation, since the first survey on this subject published by Zhang (1996), is presented. The analysis and comparison of these evaluation methods are performed according to the classification and assessment criteria for methods and performance metrics proposed in that survey. The results reveal the advantages and limitation of these new methods, and provide additional understanding about the evaluation procedure. This review presents also some novel procedures for image generation under different conditions. Compared to the results of that survey, it seems that though more attention has been attracted and more results have been obtained in these years, however, new efforts and ideas for the methodology and practical evaluation implementation are still needed.