ID 原文 译文
22605 该文利用零相关区非周期互补序列集构造了参数几乎最优的二元多子集零相关区序列集。 In this paper, multiple binary ZCZ sequence sets with inter-set Zero Corss-Correlation Zone (ZCCZ) are constructed from aperiodic complementary sequence sets with ZCZ, and the resultant binary ZCZ sequence sets are almost optimal.
22606 为解决量子彩色图像滤波问题，该文提出一种基于量子傅里叶变换的频域滤波方法。 To solve the problem of quantum color image filtering, this paper proposes a frequency domain filtering method based on Quantum Fourier Transform (QFT).
22607 首先采用新颖的增强量子描述(NEQR)方案将彩色图像描述为量子图像，然后对该量子图像实施傅里叶变换，采用基于滤波函数定义的量子 Oracle 将变换后的图像划分为不同频率的图像，最后通过逆量子傅里叶变换将这些不同频率的量子图像变换到空域，通过对空域量子图像实施测量即可得到不同频率的经典滤波图像。 Firstly, the classical color image is represented as a quantum image by Novel Enhanced Quantum Representation (NEQR) scheme, then the QFT is applied to the quantum image, and the transformed image is divided into different frequency images using quantum Oracle defined according to filter function. Finally, these quantum images of different frequencies are transformed into spatial domain by Inverter Quantum Fourier Transform (IQFT). Through the measurement, different frequency filtering images can be obtained.
22608 文中给出了具体的量子滤波线路，以彩色图像平滑、锐化、周期噪声消除为例，验证了提出方案的正确性。 In this paper, a specific quantum filter circuit is given, and the correctness of the proposed scheme is verified by taking the color image smoothing, sharpening and periodic noise elimination as an example.
22609 针对视频表情识别，静态特征不能有效描述人脸区域沿时间轴动态变化信息的局限，该文提出一种融合动态纹理信息和运动信息的表情识别方法，借鉴 LBP-TOP 原理，提出具有时空域描述能力的时空韦伯局部描述子(STWLD)来提取动态纹理信息，同时采用分块光流直方图(BHOF)描述运动信息，最后利用 SVM 对融合后的纹理和运动信息完成表情分类。 For facial expression recognition based on video sequences, the changing information of facial regions along the time axis can be described by dynamic descriptors more effectively than static descriptors. This paper proposes an expression recognition method based on the dynamic texture and motion information, and learning from the principle of Local Binary Pattern on Three Orthogonal Planes (LBP-TOP), Spatio-Temporal Weber Local Descriptor (STWLD) is proposed to describe the dynamic texture feature information of  the facial expression sequence. Moreover, using Block-based Histogram of Optical Flow features (BHOF), the motion information can be described. Through the combination of the dynamic texture and motion information, and finally SVM is applied to complete the expression classification.
22610 在 CK+和 MMI 表情数据库上的交叉实验结果表明，相比基于单一特征的识别方法，所提方法取得了更好的效果； The results of the cross experiments on the CK + and MMI expression database show that the method achieves better performance than methods using the single descriptors.
22611 与其他相关方法的对比实验也验证了该方法的优越性。 The comparison experiments with other related methods also prove the superiority of the method.
22612 该文提出一种新颖的基于二值图像微观结构模式(Binary Image Micorsructure Pattern, BIMP)表达和灰度图像微观结构二值模式(Gray Image Micorsruct Maximum Response Pattern, GIMMRP)编码方法。 A novel expression based on Binary Image Microstructure Pattern (BIMP) and Gray Image Micorstructure Maximum Response Pattern (GIMMRP) coding method is proposed.
22613 通过对图像3×3 邻域结构进行二值编码，获得图像微观结构的描述，进而选取其中的重要执行模式子集和池化操作，实现整体图像的表示。 Through the binary coding of the 3×3 neighborhood structure of the image, the description of the microstructure of the image is obtained, and then selecting the important execution mode subset and the pooling operation to realize the representation of the whole image.
22614 为了检验算法的有效性，在 ORL, YALE 两个人脸公开数据集，MNIST, USPS 两个手写数字公开数据集，以及非公开车标数据集上进行了测试，显示该方法具有很强的鉴别能力和鲁棒性，可以达到和超过很多最新算法的性能。 In order to verify the effectiveness of the algorithm, experiments are carried out on the ORL, YALE two human face data set, MNIST, USPS two handwritten digital public data sets, as well as non-public vehicle standard data set. The results show the method has strong discriminative power and robustness and can achieve better performance than many of the latest algorithms.