基于混沌蚁群算法的快速红外图像分割

提出了一种基于混沌蚁群算法优化二维模糊划分最大熵的红外图像分割方法。二维模糊划分最大熵分割方法不仅利用了灰度信息以及空间邻域信息,并且兼顾图像自身的模糊性,能取得很好的分割效果,然而最大熵的最优参量组合却很难快速准确地获得。本文将混沌蚁群优化算法应用到二维模糊划分最大熵分割方法当中,充分利用混沌蚁群算法快速寻找最优解的特点,来搜索二维模糊划分最大熵的最优参量组合。实验仿真结果表明,该方法比传统的图像分割方法有更好地分割效果,有效抑制了图像噪声对目标区域分割的干扰。

Fast infrared image segmentation based on chaos ant colony algorithm

An approach for infrared image segmentation based on fuzzy partition maximum entropy of two-dimensional histogram optimized by Chaos ant colony algorithm is proposed.Respectable segmentation result can be acquired through fuzzy partition maximum entropy because this segmentation algorithm not only utilizes image gray and spatial information but also takes account of fuzziness of image.However,it is very difficult to rapidly and exactly find optimum parameters of maximum entropy.Chaos ant colony algorithm is characteristic to rapidly find optimum solution,is used to find optimum parameters of fuzzy partition maximum entropy.The experimental results show infrared image can be segmented better by the proposed method compared with conventional one,and image noise is prevented from influencing the segmentation of target region.