期刊文献+
共找到6篇文章
< 1 >
每页显示 20 50 100
“虚拟骨骼”的性别和年龄估测的可行性研究
1
作者 S.Grabherr C.Cooper +4 位作者 S.Ulrich-Bochsler T.Uldin S.Ross L.Oesterhelweg 刘靖 《国际医学放射学杂志》 2009年第2期205-205,共1页
本文介绍了多层CT(MDCT)估测死者骨龄和性别的可行性研究。为获得虚拟骨骼。用特殊方案对22例已知死亡年龄的死者进行多层CT扫描,包括头颅、肩胛骨(包括肱骨上段)、耻骨联合和股骨上段的高分辨率成像。骨与软组织进行了二维和三维... 本文介绍了多层CT(MDCT)估测死者骨龄和性别的可行性研究。为获得虚拟骨骼。用特殊方案对22例已知死亡年龄的死者进行多层CT扫描,包括头颅、肩胛骨(包括肱骨上段)、耻骨联合和股骨上段的高分辨率成像。骨与软组织进行了二维和三维的重建。3名具不同专业经验的人类学家对所测得的数据进行了分析。 展开更多
关键词 骨龄 年龄估计 性别估计 虚拟骨骼 虚拟解剖 数字化骨骼学
下载PDF
Moment-Based Method to Estimate Image Affine Transform 被引量:1
2
作者 冯国瑞 蒋铃鸽 《Journal of Shanghai Jiaotong university(Science)》 EI 2005年第2期126-130,共5页
The estimation of affine transform is a crucial problem in the image recognition field. This paper resorted to some invariant properties under translation, rotation and scaling, and proposed a simple method to estimat... The estimation of affine transform is a crucial problem in the image recognition field. This paper resorted to some invariant properties under translation, rotation and scaling, and proposed a simple method to estimate the affine transform kernel of the two-dimensional gray image. Maps, applying to the original, produce some correlative points that can accurately reflect the affine transform feature of the image. Furthermore, unknown variables existing in the kernel of the transform are calculated. The whole scheme only refers to one-order moment, therefore, it has very good stability. 展开更多
关键词 image recognition affine transform invariant properties
下载PDF
Iterative identification of discrete-time output-error model with time delay 被引量:3
3
作者 CHEN Feng-wei LIU Tao 《Journal of Central South University》 SCIE EI CAS CSCD 2017年第3期647-654,共8页
The problem of discrete-time model identification of industrial processes with time delay was investigated.An iterative and separable method is proposed to solve this problem,that is,the rational transfer function mod... The problem of discrete-time model identification of industrial processes with time delay was investigated.An iterative and separable method is proposed to solve this problem,that is,the rational transfer function model parameters and time delay are alternately fixed to estimate each other.The instrumental variable technique is applied to guarantee consistent estimation against measurement noise.A noteworthy merit of the proposed method is that it can handle fractional time delay estimation,compared to existing methods commonly assuming that the time delay is an integer multiple of the sampling interval.The identifiability analysis for time delay is addressed and correspondingly,some guidelines are provided for practical implementation of the proposed method.Numerical and experimental examples are presented to illustrate the effectiveness of the proposed method. 展开更多
关键词 system identification output-error model instrumental variable method time delay
下载PDF
MULTI-BLOCK CHAINING-BASED AUTHENTICATION MODE
4
作者 Huang Yuhua Hu Aiqun Zhong Ziguo 《Journal of Electronics(China)》 2006年第4期564-568,共5页
A fast authentication mode based on Multi-Block Chaining (MBC) is put forward; and its security is proved. The MBC mode is for new generation block cipher algorithms. Its speed is about 13% faster than that of the aut... A fast authentication mode based on Multi-Block Chaining (MBC) is put forward; and its security is proved. The MBC mode is for new generation block cipher algorithms. Its speed is about 13% faster than that of the authentication modes in common use (for example, cipher block chaining-message authentication code mode). The dependence test results meet the requirement. The MBC mode is complete; its degree of ava-lanche effect is about 0.9993; its degree of strict avalanche criterion is 0.992 or so. The frequency test results indicate that the output generated by the MBC mode has uniformity. The binary matrix rank test results imply that it is linear independent among disjoint sub-matrices of the output. Maurer’s universal statistical test results show that the output could be significantly compressed without loss of information. Run test, spectral test, non-overlapping template matching test, overlapping template matching test, Lempel-Ziv compression test, linear complexity test, serial test, approximate entropy test, cumulative sums test, random excursions test and random excursions variant test results fulfill the requirements of all. Therefore the MBC mode has good pseudo-randomness. Thus the security of MBC mode is verified by the way of statistical evaluation. 展开更多
关键词 Block cipher algorithm Authentication mode Statistical evaluation PSEUDO-RANDOMNESS
下载PDF
Statistical Model-Based Face Pose Estimation
5
作者 戈新良 杨杰 +1 位作者 李冯 王华华 《Transactions of Tianjin University》 EI CAS 2007年第2期152-156,共5页
A robust face pose estimation approach is proposed by using face shape statistical model approach and pose parameters are represented by trigonometric functions. The face shape statistical model is firstly built by an... A robust face pose estimation approach is proposed by using face shape statistical model approach and pose parameters are represented by trigonometric functions. The face shape statistical model is firstly built by analyzing the face shapes from different people under varying poses. The shape alignment is vital in the process of building the statistical model. Then, six trigonometric functions are employed to represent the face pose parameters. Lastly, the mapping function is constructed between face image and face pose by linearly relating different parameters. The proposed approach is able to estimate different face poses using a few face training samples. Experimental results are provided to demonstrate its efficiency and accuracy. 展开更多
关键词 pose estimation face alignment statistical model face recognition
下载PDF
人脸性别约束下的深度随机森林表情识别 被引量:2
6
作者 钟良骥 廖海斌 《控制与决策》 EI CSCD 北大核心 2021年第7期1693-1698,共6页
由于人脸表情类内变化和类间干扰因素的存在,人脸表情识别仍面临着巨大挑战.提出一种基于性别条件约束随机森林的深度人脸表情识别方法,解决人脸表情识别中噪声、性别等变化和干扰问题.首先,采用深度多示例学习方法提取鲁棒性人脸特征,... 由于人脸表情类内变化和类间干扰因素的存在,人脸表情识别仍面临着巨大挑战.提出一种基于性别条件约束随机森林的深度人脸表情识别方法,解决人脸表情识别中噪声、性别等变化和干扰问题.首先,采用深度多示例学习方法提取鲁棒性人脸特征,解决人脸光照、遮挡和低分辨率等图像变化问题;其次,采用性别条件随机森林分类方法进行人脸表情分类器设计,解决人脸性别因素干扰问题.在公开的CK+、BU-3DEF、LFW人脸表情数据库上进行广泛实验结果表明:所提出方法在3大人脸数据库上分别达到了98.83%、90%、60.58%的识别率,与先进方法相比具有更好的性能和鲁棒性.另外,与其他先进的深度学习方法(需要大量训练数据库)相比,所提出方法只需要小量训练样本就能达到较好效果. 展开更多
关键词 特征提取 人脸表情识别 性别估计 深度学习 随机森林
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部