基于OLS-RBF网络的JPEG2000图像无参考质量评估方法

提出了一种适用于JPEG2000图像的无参考质量评估方法。首先结合人类视觉系统的特性,在重建图像结构纹理区域内检测边缘轮廓,并根据各个边缘点的梯度方向提取沿垂直于该梯度方向的像素集作为边缘特征;然后采用基于正交最小二乘法设计的径向基函数网络(OLS-RBF),通过边缘特征和图像主观质量的拟合,训练得到无参考客观质量评估模型,完成对JPEG2000图像的客观质量估计。与已有的一些方法的对比实验结果表明,本文方法对JPEG2000图像的客观质量评估与主观质量评估具有更好的一致性。

No-reference quality assessment metric for JPEG2000 based on OLS-RBF network

A no-reference image quality assessment metric for JPEG2000 code images is presented. First,the edge points in the structure-texture region of the reconstructed picture are detected based on the principle of Human Visual System ( HVS) . Then according to the gradient direction of the edge point,the edge feature is extracted,which is comprised of the pixels in the neighborhood of the edge point and is perpendicular to the gradient direction. Finally,a no-reference quality assessment model based on OLS-RBF network is trained to predict the quality of JPEG2000 coded images by using the image feature and the image subjective quality rating. Experimental results show that,compared with the metrics proposed by Ong and by Marziliano,the performance of the proposed metric is more consistent with subjective evaluation.