ID	原文	译文
2923	鉴于从噪声图像分解获得的原生图块集合的协方差矩阵前若干个特征值(按照升序排序)与图像噪声水平值具有强相关性，提出了一种基于主成分分析和深度神经网络的快速噪声水平估计算法。	Considering the fact that there exists the strong correlation between the first several eigenvalues (in ascend-ing order)of the covariance matrix of the raw patches extracted from a noisy image and its noise level, we proposed a novelfast multiple image-based noise level estimation (FMNLE)algorithm using the principal component analysis (PCA)and the deep neural network (DNN).
2924	该算法首先选用原生图块集合协方差矩阵前若干个特征值构成刻画图像噪声水平高低的特征矢量，	Specifically, we selected the first several eigenvalues of the raw patches to form a feature vec-tor characterizing the noise level of an image.
2925	然后在大量有代表性且已标定噪声水平值的噪声图像集合上利用深度神经网络训练预测模型以实现将特征矢量直接映射为噪声水平值，	Then, we employed deep neural network to train an estimation model on alarge number of representative natural images corrupted with known noise levels, by which the feature vector can be directly mapped into the corresponding noise level.
2926	最后为获得更高的预测准确性，采用粗精预测模型相结合的两步预测方式实现。	To obtain higher estimation accuracy, a two-step estimation strategy was adopted.
2927	实验表明:文中算法在各个噪声级别上都具有稳定的预测准确性，且执行效率非常高，作为降噪算法的前置预处理模块具有更好的综合优势。	Extensive experiments show that, the estimation accuracy of the proposed algorithm is stable at each noise level with goodefficiency, demonstrating a better comprehensive advantage as the pre-processing module for denoising algorithms.
2928	在现有基于属性值更新的动态三支决策模型上，本文充分考虑字符型属性对象在更新过程中属性知识内涵的不确定性以及对象间优异程度的差异，	According to the existing dynamic three-way decision model based on the updating of attribute values, in this paper both the uncertainty of attribute knowledge connotation and the difference of excellent degree between objects arefully considered in the process of updating the object.
2929	首先定义字符型属性对象的经验值和经验综合评价值的概念来初步刻画对象，再用修正值来表示对象的知识内涵;	More concretely, both the experience value of character attribute ob-jects and the concept on comprehensive evaluation value of experience are firstly defined to describe the object initially, and the knowledge connotation of the object is expressed by the revised value of character attribute objects.
2930	通过修正值计算出的基于欧氏距离的最优贴近度作为对象的修正综合评价值;	Next, the optimal closeness degree based on the Euclidean distance calculated by the revised value is used as the revised comprehensive evalua-tion value of the object.
2931	然后，给出了字符型属性对象的动态特征的提取方法，建立了动态三支决策模型。	Then, the extraction method of dynamic feature on objects with character attributes is presented, and a dynamic three-way decision model is established.
2932	最后，通过大量的仿真实验验证了模型的高效性和适用性。	Finally, a large number of simulation experiments have been made to val-idate the efficiency and applicability of the proposed model.