为了获取生物组织的光学特性参量，采用CCD无损测量系统来获得生物组织的漫反射图像,通过数据分析获取组织表面的漫射光分布，首先对具有不同光学特性参量的组织模拟液进行测量,用实验所得数据训练神经网络，并用另一组实验数据对神经网络的有效性和精确度进行了验证，然后对牛肉、猪肉以及人体表皮组织在633nm光照下进行了测量, 由经实验数据训练的神经网络反演获得生物组织的光学特性参量。结果表明，神经网络能够正确反演不同组织的光学特性参量, 并具有较高的精度。

In order to acquire the optical properties (scattering and absorption coefficients) of biological tissue, the CCD non-invasive measurement equipment was used to measure the image of diffuse reflectance of biologrcal tissue. The spatially resolved diffuse reflectance of the tissue was acquired by analyzing the image. One set of experimental data on tissue phantoms were used to train a neural network which was used to extract the optical properties. The accuracy of the neural network was investigated and validated by another set of experimental data. The optical properties of bovine muscle, pig muscle and human skin tissue under 633nm laser irradiation were also determined by the network which was trained by the experiment. The result shows the neural network can estimate the optical properties of different tissues with high accuracy.