基于支持向量机的图像预测编码算法

Predictive Coding Based on Support Vector Machine

提出了一种利用支持向量机(SVM)构建预测器的图像压缩预测编码算法。该算法将遗传算法引入支持向量机中,在自学习的过程中,能够自动调整SVM的核参数,获取准确的图像信息。通过仿真试验,并与传统预测编码方法、神经网络预测编码方法进行比较,结果证明该算法恢复图像效果最好。

This paper presents a predictive coding model based on support vector machine （SVM）. The model introduced genetic algorism into SVM, so it can adaptively adjust kernel parameters of SVM and obtain exact image information. After simulated and compared with other predictive coding models, the model shows much better performance on the quality of reconstruction pictures.