基于Tsallis熵的自适应红外图像边缘检测方法

Adaptive Edge Detection Method Based on Tsallis Entropy of Infrared Image

针对红外图像边缘检测这一难题,结合红外图像的特点,提出了基于Tsallis熵的自适应红外图像边缘检测方法.该方法分别计算图像子空间的边缘与非边缘的Tsallis熵,根据子空间最优Tsallis熵,构造出子空间最佳阈值的评价函数,根据评价函数,选择不同方向的边缘检测模板,增强了图像的边缘信息,从而避免了单一模板造成的边缘丢失现象.实验结果表明,与传统的边缘检测方法相比,该方法对于红外图像可以最大程度上抑制噪声,有效地提高图像的边缘检测效果.

Pointing at the difficulty in the edge detection of infrared image,the characteristics of the infrared image and its gradient image are analyzed,a adaptive edge detecting algorithm based on Tsallis entropy of infrared image is proposed.This method computes the Tsallis entropy of edge and non-edge of local-image differently,based on the best Tsallis entropy of local image,a evaluation function is proposed.Based on the evaluation,the different structure of edge detecting is selected,the image edge information is enhanced,and avoids the edge missing.Experiment results show that,compared with the traditional edge detecting method,this method decreases the noise of infrared image as possible as it can and enhances image edge.