ID 原文 译文
1453 实验研究验证了本文方法的合理性。 Result of experiment verify validity of our proposed methods.
1454 糖尿病视网膜病变是成年人致盲首因，视网膜血管分割是诊断糖尿病视网膜病变的基础。 Diabetic retinopathy is the leading cause of blindness in adults, and the retinal vessels segmentation is thebasis for the diagnosis of diabetic retinopathy.
1455 为提高视网膜血管分割准确性，提出一种基于多模型融合和区域迭代生长的视网膜血管自动分割算法。 To improve the accuracy of retinal vessels segmentation, an automatic retinalvessel segmentation method based on multi-model fusion and region iterative growth is proposed.
1456 首先，预处理后分别构建数学形态学、匹配滤波器、尺度空间分析、多尺度线检测和神经网络模型初步分割视网膜血管，为减少噪声取五个分割结果的均值作为初步输出。 Firstly, the mathematicalmorphology, matched filter, scale-space analysis, multi-scale line-detection and neural network models were established tosegment retinal vessels initially, and the mean value of the five segmentation results was taken as the preliminary output toreduce the noise.
1457 其次，设计掩膜分离渗出物和视盘，将数学形态学模型分割结果替换掩膜白色区域，并融合初步输出生成组合结果。 Secondly, after exudates and optic disc were separated with a mask developed, the white areas in the maskwere replaced by the segmentation result of the mathematical morphology model, and then the combined result was generatedwith replaced mask and preliminary output fused.
1458 最后，考虑视网膜血管先验知识，对组合结果阈值分割和区域迭代生长后获取最终结果。 Finally, considering the prior knowledge of retinal vessels, final resultswere obtained after threshold and region iterative growth.
1459 实验结果表明，该算法分割 DRIVE 和 STARE 眼底图像库视网膜血管的检测精度、敏感度和特异性分别为 09457、0.7843、0.9815 以及 0.9472、0.7826、0.9803，优于多数经典算法。 The experimental results demonstrate that the accuracy, sensitivityand specificity for segmenting the retinal vessels in the DRIVE and STARE fundus image datasets are 0. 9457, 0. 7843, 0. 9815 and 0. 9472, 0. 7826 and 0. 9803, respectively, which is superior to most classical algorithms.
1460 针对工作于 underlay 模式的认知无线网络(CRN，Cognitive Radio Network )上行功率控制问题，本文提出一种基于多天线波束赋形，由认知基站和认知用户联合优化的分布式上行功率控制算法。 To solve the uplink power control problem in underlay cognitive radio network (CRN), this paper propo-ses a distributed uplink power control algorithm based on multi-antenna beamforming, which is jointly optimized by cogni-tive base station and secondary users.
1461 联合优化的具体步骤为 The specific steps of joint optimization are as follows.
1462 认知基站通过求解最大广义特征值问题完成多天线波束赋形优化; Cognitive base station accom-plishes multi-antenna beamforming optimization by solving the maximum generalized eigenvalue problem.