中文摘要：

运动模糊是影响LCD图像质量的主要问题。LCD运动模糊是由LCD慢响应、“抽样一保持”特性与HVS的低通滤波特性所引起。本文提出了一种基于最小二乘支持向量机（LS-SVM）的运动去模糊方法。该算法从系统辨识角度，通过对样本数据的训练，构造预补偿系统的预测PSF模型。最后，使用该预测PSF模型实现运动图像的去模糊过程。仿真结果显示，该算法具有比较理想的效果，可以应用于实际的LCD运动图像去模糊。

英文摘要：

The primary＂ image quality issues of LCD is the motion blur. LCD motion blur is caused jointly by the slow LCD＇ s temporal response and the hold-type LCD＇ s rendering method together with the motion pursuing function of human visual system （HVS）. In this paper we develop a method for motion blur reduction using the Least Square Support Vector Machine（LS-SVM） algorithm. From the point of system identification, this algorithm constructs the predictive PSF model of the pre-compensation system through training the sample data. And then, using the predictive PSF model to realize the motion de-blurring. Simulation results show that the algorithm has a good effect, and can be used for actual LCD motion de-blurring.