ID 原文 译文
16785 结果表明越大的规模并不一定能够带来越高的能效， The results show thatlarger scale CSPLA does not necessarily bring higher energy efficiency.
16786 为取得映射的最佳能效，阵列的规模参数应当与具体的硬件资源限制和密码算法运算需求相匹配，CSPLA规模为4×4～4×6时映射取得最优能效，AES算法最优能效为33.68Mbps/mW， When the CSPLA scale is about4×4～4×6 which achieves the best energy efficiency. In order to obtain the best energy efficiency, the scaleparameter of the array should match the specific hardware resource constraints and cryptographic algorithmparameters. The optimal energy efficiency of AES algorithm is 33.68 Mbps/mW.
16787 对比其它密码处理结构，CSPLA具有较优的能效特性。 CSPLA has better energyefficiency characteristics compared with other cryptographic processing structures.
16788 为解决眼镜遮挡会降低人脸识别性能的难点，借鉴深度卷积神经网络在超分辨率方面的成功应用，该文提出一种用于细粒度人脸识别的眼镜自动去除方法ERCNN。 In order to solve the problem that eyeglasses reduce often the performance of face recognition, based on the successful application of deep convolution neural network in super-resolution, this paper proposes an automatic eyeglasses removal method ERCNN (Eyeglasses Removal CNN) for fine-grained face recognition.
16789 用卷积层、池化层、MFM特征选取模块和反卷积层设计ERCNN网络模型，自动学习戴眼镜和未戴眼镜人脸图像对之间的映射关系，实现端到端的眼镜去除。 Specifically, the ERCNN network which is designed based on the convolution layer, pool layer, MFM (MaxFeature Map)feature selection module and deconvolution layer, are automatically learned the mappingrelationship between facial images with eyeglasses and their counterparts without eyeglasses to realize end-to-end eyeglasses removal.
16790 然后，收集大量监控场景下的人脸图像，以及互联网上公开的人脸图像作为训练集； Then, massive facial images are captured through surveillance equipment and collectedfrom the Internet as the training set.
16791 同时构建SLLFW数据集，作为眼镜去除和人脸识别的测试集。 And, SLLFW data set is established, which is used as the test set ofeyeglasses removal and face recognition.
16792 最后，通过与传统的眼镜去除方法进行对比试验，该文算法的各项评价指标优于传统方法，能有效的去除真实人脸图像中眼镜； The experiment show that the proposed method can better effectively remove the eyeglasses from the real facial image than the traditional eyeglasses removal methods, and the evaluation index of the method is better than other methods.
16793 同时在SLLFW人脸数据集上形成的全框眼镜、半框眼镜和无框眼镜人脸数据集上对多种人脸识别算法进行对比试验。 In addition, several face recognition methods are tested separately on the facial images formed by SLLFW data set.
16794 试验表明，在FAR为1%的情况下，利用该文方法对F-SLLFW, H-SLLFW和R-SLLFW数据集的人脸图像进行眼镜去除后，SphereFace算法的TAR分别达到90.05%,91.14%和92.33%，比未去除眼镜的识别率分别提高了3.92%, 3.08%和1.26%； Experiments show that when the FAR (False Accept Rate) is 1%, the TAR (True Accept Rate) of the Sphereface method reaches 90.05%, 91.14% and92.33%, which is 3.92%, 3.08% and 1.26% higher than the Sphereface method is not used to remove theeyeglasses from the F-SLLFW, H-SLLF and R-SLLFW, respectively.