ID 原文 译文
4373 针对现有图像复制粘贴篡改检测算法计算复杂度过高的问题，提出了一种基于分组尺度不变特征变换的图像复制粘贴篡改快速检测算法。 Aiming at the high computational complexity of the existing copy-move image forgery detection algorithm, acopy-move forgery detection algorithm based on group scale-invariant feature transform (SIFT) was proposed.
4374 首先，利用简单线性迭代聚类将输入图像分割成非重叠且不规则的块； Firstly, thesimple linear iterative clustering (SLIC) was utilized to divide the input image into non-overlapping and irregular blocks.
4375 然后，根据图像块内结构张量属性将其分为平坦块、边缘块和角点块，提取图像块内的 SIFT 特征点作为块特征； Secondly, the structure tensor was introduced to classify each block as flat blocks, edge blocks and corner blocks, and then the SIFT feature points extracted from the block were taken as the block features.
4376 最后，通过块特征的类间匹配定位篡改区域。 Finally, the forgery was located by theinter-class matching of the block features.
4377 所提算法通过图像块分类和类间匹配，在保证检测效果的同时，有效地降低了特征匹配定位篡改区域阶段的时间复杂度。 By means of inter-class matching and feature point matching, the time complexity of the proposed copy-move forgery detection algorithm in feature matching and locating forgery region was effectively re-duced while guaranteeing the detection effect.
4378 实验结果表明，所提算法检测准确率为 97.79%，召回率为 90.34%，F 值为 93.59%；图像尺寸为 1 024 像素×768 像素时算法时间复杂度为 12.72 s，图像尺寸为 3 000 像素×2 000 像素时算法时间复杂度为 639.93 s。 The experimental results show that the accuracy of the proposed algorithm is 97.79%, the recall rate is 90.34%, and the F score is 93.59%, the detecting time for the image with size of  1024 768  is12.72 s, and the detecting time for the image with size of  3000 2000  was 639.93 s.
4379 与已有的复制粘贴算法相比，所提算法能够快速精准地定位篡改区域，且具有较好的稳健性。 Compared with the existing copy-movealgorithm, the proposed algorithm can locate the forgery region quickly and accurately, and has high robustness.
4380 针对蜂窝系统下 D2D 中继辅助通信的能量效率优化问题，在保证蜂窝用户与 D2D 用户服务质量的条件下，提出了一种能效优化算法。 In order to optimize the energy efficiency for relay-aided D2D communication underlaying cellular network,an algorithm was proposed while guaranteeing the quality of service of D2D users and cellular users.
4381 首先，以最大化系统中总 D2D 用户能效为目标，将优化问题建模为一个混合整数非线性规划问题。 Firstly, the problemwas formulated as a mixed integer nonlinear fractional programming problem, with the goal of maximizing the energy ef-ficiency of all D2D users.
4382 然后，将能效优化问题转化为功率控制、中继选择和信道分配 3 个子问题分别进行求解。 Then, the maximizing energy efficiency problem was divided into three sub-problems, such aspower allocation, relay selection and subcarrier assignment.