Abstract: Traditional television picture quality evaluation methods suffer from disadvantages of being time-consuming and costly as subjective methods.An expert system is proposed for efficient image quality evaluation.Multiple extracted features are based on multi-feature fusion and Support Vector Machines（SVM）.The SVM is trained by multi-feature extracted from the pictures and then it can evaluate the TV picture quality intelligently.The experiment results demonstrate that the method can greatly improve the efficiency and accuracy of evaluation.

摘要： 传统的电视画质测评采用主观评价方法，这种方法耗时长，费用高，并且受环境、评测人员等的影响较大。建立一个基于多特征融合和支持向量机（SVM）的画质测评专家系统，采用图像处理的方法对由电视屏幕采集的图像进行处理，并提取相应的特征来训练SVM，训练后的系统能够智能地评价电视画质。实验表明，该方法可以客观、高效地评价画质，评价结果与主观评价结果基本一致。