基于模糊CMAC神经网络的医学舌苔图像检索

The Retrieval of the Medical Tongue-coating Images Using Self-organized Map Neural Network

笔者提出了一种基于模糊CMAC神经网络的医学舌苔图像检索方法。该法利用CMAC网络,实现彩色图像直方图的模糊相关求和,并在此过程中自动调整加权算法中特征色的加权因子,使舌苔图像的检索能针对几大类标准进行,提高了检索效率。实验结果表明,与过去根据经验设定参数的方法相比,本法具有高效、准确,对阴影、反光现象不敏感等特点。

A retrieval way for medical tongue-coating images based on fuzzy CMAC neural network is presented in this paper. With the weight strength of the CMAC network, the number and the regarded feature-colors are adjusted self-adaptively, during the process of calculating the confused relative factors＇ summary of the color-images, so that the retrieval for tongue-coating images concentrates efficiently on several distinct kinds. The experimental results show, comparing with the manual way, the new way is more accurate and effective, and less relative with the illumination of the images.