基于聚类算法的红外图像伪彩色增强

Infrared Image Pseudo-Color Enhancement Based on Clustering Algorithm

文中根据红外图像的特点,提出了一种基于K-均值聚类的红外图像伪彩色增强的新算法。该算法通过对红外图像灰度数据的统计学习,产生初始聚类中心,采用K-均值聚类算法对灰度进行聚类,并根据伪彩色编码的节点对聚类结果分段实现伪彩色的自适应分配。实验结果表明,该方法可增强红外图像的细节信息和层次感,具有更好的视觉效果。

A new infrared image pseudo-color enhancement algorithm is presented based on K-means clustering. This method firstly does the statistic learning of the gray pixels in the original infrared image in order to create the initial cluster eenters. Secondly, the data of gray in the original image are clustered by K-means with the initial cluster centers. Lastly, the infrared image is self-adaptively enhancement according to the result of elustering and the pseudocolor encoding separated into several sections. The experimental results indicate that this method could further improve the detail information, arrangement, and visual effect.