基于区域差异性的激光热成像图像分割

Laser thermal imaging image segmentation based on regional difference

为了解决激光热成像图像分割过程存在的一些缺陷,提升图像分割准确性,设计了基于区域差异性的激光热成像图像分割方法。首先采集激光热成像图像,采用双边滤波技术对原始激光热成像图像进行预处理,消除噪声对激光热成像图像分割的干扰,然后根据激光热成像图像区域之间差异生成种子区域,依据相似度量准则获取热成像图像的种子区域生长,并确定种子区域生长边界的阈值,根据阈值进行激光热成像图像分割,最后采用区域合并法对小区域进行合成得到激光热成像图像分割结果,并进行了激光热成像图像分割的仿真实验。结果表明,本方法的激光热成像图像分割准确率超越90%,激光热成像图像分割时间大约为8 s,获得了比其他方法更优的激光热成像图像分割。

In order to solve some defects in the process of laser thermal imaging image segmentation and improve the accuracy of image segmentation, a laser thermal imaging image segmentation method based on regional difference is designed. Firstly, the laser thermal imaging image is collected, and the bilateral filtering technology is used to preprocess the original laser thermal imaging image to eliminate the interference of noise on the laser thermal imaging image segmentation. Then, according to the difference between the laser thermal imaging image regions, the seed region growth of the thermal imaging image is obtained according to the similarity measurement criterion, and the threshold of the seed region growth boundary is determined, laser thermal imaging image is segmented according to the threshold. Finally, the small regions are combined by the region merging method to obtain the laser thermal imaging image segmentation results, and the simulation experiment of laser thermal imaging image segmentation is carried out. The results show that the laser thermal imaging image segmentation accuracy of this method is 90%, and the laser thermal imaging image segmentation time is about 8 s, which is better than other methods.