基于模糊积分的图像分割算法融合

Multiple image partition algorithm fusion based on fuzzy integral

提出了一种基于多分类器融合的阈值分割方法,采用模糊积分将多种阈值分割算法的结果进行融合,其区别于现有分类器融合算法之处在于,融合过程不仅取决于各个分类器(分割算法)的判决输出,而且与各个分类器的判决能力有关。各个分类器的判决能力用模糊测度表示,它可以解释为单个分类器判决对最终融合判决的重要程度。通过使用一组手工分割的测试图像进行算法评估,结果表明,所提出的融合算法性能不仅优于单个阈值分割算法,而且优于基于多数表决和算术平均的分类器融合算法。

A new threshold partition method based on multiple classifier fusion is proposed. It uses fuzzy integral to integrate the outputs of multiple threshold partition algorithms. The proposed method differs from the traditional classifier fusion methods in that its fusion decision not only depending on the individual classifier＇s output, but also incorporating the uncertainty of the classifier＇s ability to make decision. The classifier＇s decision making ability is represented by fuzzy measurement, which can be interpreted as the importance of the individual classifier＇s local decision to the final decision. Evaluated by a set of ground-truth segmented non-destructive images, the averaging validation index shows that the proposed method takes advantages over individual threshold partition algorithm, also over majority voting and averaging fusion methods.