摘要
高温物体的温度不同,通过数码相机摄取的高温物体的颜色也不同,由此提出一种基于神经网络的图像颜色测温方法.选取RGB模型的R、G和B作为模式特征向量,用BP网络拟合高温物体的颜色和温度之间的非线性关系.实验结果表明,该方法精度高,运行速度快,切实可行.
Based on the fact that different high -temperature object images captured by the digital camera correspond with the different colors, a method of temperature measurement of image color based on neural network is proposed. R, G and B of the RGB model are used as the pattern character vectors. BP neural network is used to approximate the nonlinear relations between the color and the temperature of high - temperature object. The experiment result shows that the method is feasible with high accuracy and quick running rate.
出处
《河南理工大学学报（自然科学版）》
CAS
2008年第2期206-210,共5页
Journal of Henan Polytechnic University（Natural Science）
关键词
温度测量
BP神经网络
颜色模型
temperature measurement
BP neural network
color mode
