光谱图像中药成分含量检测仿真研究

Simulation Research for Spectral Image Chinese Native Medicine Ingredient Content Detection

光谱图像中药成分含量进行准确检测,可以使药物制剂安全、有效、可控。进行中药成分含量检测时,需要对光谱图像中药成分含量数据进行预处理,获取中药成分先验光谱信息,以此为基础,对中药成分含量独立成分分析,完成成分含量检测,但采用传统算法进行中药成分含量检测时,中药成分先验光谱信息在实际处理中很难得到,存在检测误差大的问题。提出一种光谱图像中药成分含量检测方法。上述方法先利用迭代误差分析原理对高光谱图像中药成分含量数据进行处理,获取高光谱图像数据的异常端元,并进行中药成分含量独立成分分析,基于平均局部奇异度选择含异常数据较多的中药含量成份,并得到该中药成分含量的丰度图像,从而完成对中药成分含量检测。仿真结果表明,改进方法可以提高光谱图像中药含量优化检测的有效性和稳定性。

A content detection method of Chinese herbal medicinal ingredient in spectrum image is proposed. Firstly, the iterative error analysis theory is used to deal with the content data of Chinese herbal medicinal ingredient in hyperspectral image, and the abnormal end member of hyperspectral image data is obtained. The independent com- ponent of Chinese herbal medicinal ingredient content is also analyzed. Then the Chinese herbal medicinal ingredient content with many abnormal data is chosen based on average local singularity degree, and the abundance image of Chinese herbal medicinal ingredient content is obtained. Finally, the content detection is completed. The simulation results show that the modified method can improve the effectiveness and stability of content optimization detection.