ID 原文 译文
24495 为提高各种不同特殊场景下的模糊人脸识别精确性和鲁棒性，本文提出一种基于迹变换和旋转增量调制编码的特征提取方法。 For the accuracy and robustness of the blurry face image recognition in various special scenarios; this paper proposes a novel rotation delta modulation texture extraction method based on trace transform and delta modulation encoding.
24496 该方法将通信语音编码技术与图像变换技术相结合，首先通过迹线旋转扫描整幅图像，并对迹线上的采样信息进行增量调制编码，从而获得多角度的全局有序结构特征，然后用支持向量机对样本图像的这些特征进行训练以分类并识别图像。 The method combines the communication speech coding with the image transformation technology. Firstly, the whole image is scanned by the rotating trace line based on trace transformation theory. Secondly, the sampled pixels on the traceline are encoded using delta modulation technology. The global ordered structure features are obtained in various angles. Finally, the features are trained by support vector machine for blurry face image classification and recognition.
24497 实验结果表明，在各种不同模糊级的低质量人脸数据库上，本文方法对不同光照变化、不同拍摄角度、不同遮挡等不同场景的人脸图像均能取得较好的识别效果，与一些传统方法相比识别性能大幅提升，相对于 VGGNet 和 Sphereface 两种先进方法在三组不同模糊度测试图像集的平均识别率分别提高 2.18% 和 2.20%，具有更高的识别精度和更好的鲁棒性。 The experimental results indicate the proposed method has the better performance of blurry face image recognition under illumination fluctuations, various camera angles and image occlusions, and so on, on a variety of low-quality face image sets with different blur levels. The average recognition ratio are increased 2.18% and 2.20% compared to VGG and Sphereface methods on the face image sets with three blur levels, which indicates the proposed method has the higher accuracy and better robustness.
24498 为解决传统互补序列集中序列数目受限的问题，近年来有学者提出集间低相关性完全互补码(CCC，Complete Complementary Code)的概念。 In order to solve the problem of the limited number of sequences in the traditional complementary sequence sets, some scholars have proposed the concept of complete complementary code sets (CCCs) with low inter-set cross-correlation in recent years.
24499 集间低相关性的完全互补码具有良好的非周期自相关和互相关特性，作为多小区多载波码分多址(MC-CDMA, Multi-Carrier Code Division Multiple Access)通信系统中的扩频码可有效消除小区内的干扰，同时也可以抑制小区间的干扰。 Complete complementary code sets with low inter-set cross-correlation have perfect aperiodic auto-correlation and cross-correlation properties. As the spreading code in the multi-cell MC-CDMA communication system, CCCs can effectively eliminate intra-cell interference and suppress inter-cell interference.
24500 该文提出两类具有集间低相关性的完全互补码集的构造方法，得到的序列集具有以下特性：(1)每个码集都是一个参数为(N,N,N )-CCC的完全互补码集； Two constructions of complete complementary code sets with low inter-set correlation are developed, and the resultant complementary sequence sets have the following properties: (1) each set is a complete complementary code set with parameters (N,N,N )-CCC;
24501 (2)不同集合的互补序列具有低相关性。 (2) complementary sequences from different sets have low correlation functions.
24502 将多个完全互补码集合并，可以得到参数达到渐进最优的准互补序列集(QCSS, Quasi-Complementary Sequence Set)。 Finally, an asymptotically optimal quasi-complementary sequence set is obtained when these multiple complete complementary code sets are combined.
24503 针对复杂地理场景下非均匀杂波造成多通道 SAR-GMTI（Synthetic Aperture Radar Ground Moving TargetIndicator，合成孔径雷达动目标指示）系统杂波抑制性能下降的问题，本文提出一种距离-多普勒-频带域三维自适应加权惩罚马尔科夫场（Three Dimension Adaptive Weighted Penalty Markov Random Field，3D-AWP-MRF）分类辅助的 SAR-GMTI杂波抑制方法。 To address the problem that the clutter suppression performance of a multichannel synthetic aperture radar ground moving target indicator (SAR-GMTI) system is reduced due to non-uniform clutter in a complex geographical scene, we propose a multichannel SAR-GMTI clutter suppression method assisted by Range-Doppler-Band three dimension adaptive weighted penalty markov random field (3D-AWP-MRF) classification.
24504 利用地物类型在距离-多普勒-频带三维 SAR图像空间的马尔科夫性，构造了包含空间距离、类间Fisher 距离、局部粗糙度距离和梯度方向距离的自适应加权惩罚函数。 Firstly, an adaptive weighted penalty function is constructed using the markov properties of the feature types in the Range-Doppler-Band 3D SAR image domain. Spatial distance, inter-class Fisher distance, local roughness distance, and gradient direction distance are included.