基于最小二乘支持向量机的模糊图像恢复

A blurred image restoration method based on LS-SVM

针对模糊图像恢复问题,提出了一种基于最小二乘支持向量机的模糊图像恢复算法。该方法利用最小二乘支持向量机的非线性映射能力,通过训练样本对的学习训练,在模糊图像与清晰图像之间建立映射关系对测试样本进行恢复。实际图像恢复实验表明,得到的恢复图像在视觉上和定量分析上都获得了比较好的效果。与神经网络方法相比,最小二乘支持向量机克服了神经网络的模型选择与过学习问题、局部极小问题等。

A new blurred image restoration method was presented and investigated based on least squares support vector machine （LS- SVM）. The mapping relationship between degenerated image and clear image was established by training support vector machine. Experimen- tal results show that this method has a satisfying restoration effect both in visual impression and quantitative analysis. Compared with neural network, the LS-SVM has prominent advantages in selecting model, overcoming over-fitting and local minimum, etc.