阴极射线管色度转换的神经网络模型

利用神经网络技术实现了从阴极射线管(CRT)的R、G和B空间到CIE的标准色度空间的转换.用拟牛顿法训练网络模型,建立了从CRT的R、G和B到CIE的X、Y和Z色度空间变换的3 10 10 3神经网络模型.采用7点LOG空间分布方案的343个训练样本建模的试验表明,收敛性与训练时间及模型精度均优于前人采用3~4个隐层的方案,343个训练样本、216个检验样本和64组测试样本的平均转换精度分别为0.6个CIELUV色差单位,说明该模型的泛化能力很好.

Cathode ray tube color conversion model by use of neural networks

The color calibration in CRT(cathode ray tube) space is the base of color standard in computers.The color notation conversion from the RGB space of the CRT to the XYZ space of CIE system is carried out by using neural network.The neural network topology with a few neurons in two hidden layers,and quasiNewton method are applied.With the neural network based model,343 training set data and 216 verification set data according to the principle with LOG space and 64 data sets according to even distribution are used to verify the training results and test the modeling performance.The case study shows that the converging speed,the training time and the accuracy of the model with two hidden layers are very satisfactory.The average precision of the color notation conversion of the model established is less than 0.6 CIELUV unit.