【作者】 姜巧巧； 钱昆明；

【Author】 Jiang Qiaoqiao~1 Qian Kunming~2 School of Electronic & Information Engineering,Dalian University of Technology,116024

【机构】 大连理工大学电子与信息工程学院；

【摘要】 本文提出了一种基于 Renyi 熵的阈值分割新方法。该方法首先计算代表目标和代表背景的熵值,然后求出两熵之和以及两熵之差的绝对值,最佳阈值对应于两者比值的最大值。Renyi 熵比传统的 Shannon 熵多了一个参数,此参数使得 Renyi 熵能够更灵活地处理多种类型的图像。按照本文方法进行实验,结果显示该算法比传统的 Shannon 熵方法更有效。更多还原

【Abstract】 A threshold segmentation algorithm based on Renyi’s entropy is presented.The algorithm calculates the entropy of object and the entropy of the background firstly,then the value of the two entropies’ sum and the absolute value of difference between the two entropies is gained,and the threshold value is corresponding to the maximum which is the ratio of the sum to the absolute value.Renyi’s entropy has an additional parameter comparing to Shannon entropy.The additional parameter makes it realizable to process more types of image.The simulating result shows that this algorithm is better than Shannon entropy algorithm.更多还原