论文部分内容阅读
通过模拟人脑视觉神经接收视觉信息形成表面感知的处理机制,提出一种基于大脑层状皮质模型的全参考立体图像的图像质量评价(IQA)方法。首先,分析大脑形成表面感知的过程,提出可运用于立体图像的IQA的层状皮质模型;然后依据模型得到各层的响应输出,构建感知特征向量;最后利用机器学习算法,建立特征和质量的关系模型,预测立体图像质量。实验结果表明,本文方法在对称立体图像库上的Pearson线性相关系数(PLCC)和Spearman等级系数(SROCC)高于0.91,在非对称库上高于0.93。与现有的相关方法相比,本文方法与主观评价更加吻合,更适合立体图像的评价和优化。
By simulating the processing mechanism of human visual nerve receiving visual information to form surface perception, an image quality evaluation (IQA) method based on cerebral cortical model of the whole reference stereoscopic image is proposed. Firstly, we analyze the process of brain surface formation perception and propose a layered cortical model of IQA that can be applied to stereoscopic images. Then, the response output of each layer is obtained according to the model to construct the perceived feature vector. Finally, the machine learning algorithm is used to establish the features and quality Relationship model to predict the stereoscopic image quality. The experimental results show that the Pearson linear correlation coefficient (PLCC) and Spearman rank coefficient (SROCC) of the proposed method are higher than 0.91 in the symmetric stereo image database and higher than 0.93 in the asymmetric library. Compared with the existing related methods, this method is more consistent with the subjective evaluation, which is more suitable for the evaluation and optimization of stereo images.