助手标题  
全文文献 工具书 数字 学术定义 翻译助手 学术趋势 更多
查询帮助
意见反馈
   旋转不变识别 的翻译结果: 查询用时:0.21秒
图标索引 在分类学科中查询
所有学科
计算机软件及计算机应用
更多类别查询

图标索引 历史查询
 

旋转不变识别
相关语句
  “旋转不变识别”译为未确定词的双语例句
     Rotation-invariant Discrimination Between Almost Similar Patterns
     相似图象的旋转不变识别
短句来源
     Three-dimensional object recognition with rotation-invariant based on Moire fringe
     基于莫尔条纹的三维物体的旋转不变识别
短句来源
     A linear discrimination function (d(w, x)=w′x) is presented to classify two aircrafts (the bomber and the fighter) with rotation invariance.
     提出利用线性判别函数,d(x)=W′x,对轰炸机和战斗机两类目标进行旋转不变识别
短句来源
     Multi objects classification with in plane(2 D) and out plane(3 D) rotation invariance is implemented by using this general discrimination function and neural network model. The computer simulation shows that it is an effective method for classifying multi objects with rotation invariance. One of the opto electronics recognition systems is presented to implement this function and model.
     提出利用径向基函数构造广义判别函数及神经网络模型,显示了模式识别与神经网络之间的密切联系.利用此函数和模型实现了多目标的面内(二维旋转)、面外(三维空间旋转)旋转不变识别,计算机模拟表明,对于旋转不变识别这是一个很有效的方法.一个光电混合系统被提出实现此旋转不变识别方法.
短句来源
     In this paper a method of the three-dimensional object recognition with rotation-invariant based on moire fringe is proposed.
     本文提出一种基于莫尔条纹的三维物体旋转不变识别方法。
短句来源
  相似匹配句对
     Rotation-invariant Discrimination Between Almost Similar Patterns
     相似图象的旋转识别
短句来源
     Rotation Invariant Pattern Recognition Based on Wiener Filter
     基于维纳滤波的旋转相关识别
短句来源
     A New Method For Rotation-Invariant Texture Classification Based on Mathematical Morphogy
     基于数学形态的旋转纹理识别方法
短句来源
     Recognition of character strings based on projection moment invariant
     基于旋转投影矩的字符串识别方法
短句来源
     SHIFT, ROTATION AND SCALE INVARIANT OPTICAL NEURAL NETWORK RECOGNITION SYSTEM
     平移、旋转及尺度光学神经网络识别系统
短句来源
查询“旋转不变识别”译词为用户自定义的双语例句

    我想查看译文中含有:的双语例句
例句
没有找到相关例句


Using a circular harmonic filter or a phase-only circular harmnnic filter for rotation-invariant discrimination between almost similar patterns, a new method for determining the circular harmonic expansion center is presented. This method may obtain better discrimination compared with the conventional method; especially, it is appropriate to phase-only circular harmonic filter. In addition, the results of the computer simulation are given.

提出一种选取圆谐展开中心的新方法,用于圆谐滤波器和纯位相圆谐滤波器作相似图象的旋转不变识别中,这种方法可以提高图象的识别力,对纯位相圆谐滤波器特别有效,同时给出计算机模拟实验的结果。

A hopfield type neural network was applied to optimize binary correlation synthetic discriminant functions (SDFs). Rotation invariance is achieved while the target object rotates in a certain angle range and a ratio for judgement which is defined as the ratio of the peak value to the average absolute value of a specific point set is given. The optimized binary SDFs (BSDFs) provide the control of the sidelobe levels and the expected shape of the output correlation functions as well as its peak intensity.The simulation...

A hopfield type neural network was applied to optimize binary correlation synthetic discriminant functions (SDFs). Rotation invariance is achieved while the target object rotates in a certain angle range and a ratio for judgement which is defined as the ratio of the peak value to the average absolute value of a specific point set is given. The optimized binary SDFs (BSDFs) provide the control of the sidelobe levels and the expected shape of the output correlation functions as well as its peak intensity.The simulation result shows that when the target object is presented to the optimized filter, not only the correlation peak is as high as expected and higher than that of the nontarget objects, but also the order of the magnitude of the ratio for judgement is at least 1 greater than that of the non-target objects. The recognition ability of the filter is very Strong.

根据Hopfield神经网络的优化功能,对综合鉴别函数进行二元优化,使相关输出具有期望的形状及峰值大小,从而实现旋转不变识别,并定义了一个判别依据——判别比.计算机模拟的结果表明,目标物体通过优化的二元滤波器后,不仅具有期望输出,而且判别比要比伪目标物体至少大一个量级.

Complicated nonlinear transformations are realized with the feedforward neural network, of which the input elements are connected nonlinearly. The learning rules of the network are derived, and the conditions of translation invariance, scale invariance and rotation invariance pattern recognition are constructed in the network during the learning procedure.Furthermore, with the help of the idea of equivalent weight subset proposed, the network is made much simple and the learning time is reduced.

利用前向网络输入元素非线性关联的方法实现了从输入模式空间到输出标识空间复杂的非线性变换.推导了学习方法,并在学习过程中把模式的平移不变识别、比例不变识别及旋转不变识别等条件构造在神经网络的权结构之中,使其具有模式不变识别能力,同时借助等权类的概念,极大地简化了网络的拓扑结构,降低了学习时间

 
<< 更多相关文摘    
图标索引 相关查询

 


 
CNKI小工具
在英文学术搜索中查有关旋转不变识别的内容
在知识搜索中查有关旋转不变识别的内容
在数字搜索中查有关旋转不变识别的内容
在概念知识元中查有关旋转不变识别的内容
在学术趋势中查有关旋转不变识别的内容
 
 

CNKI主页设CNKI翻译助手为主页 | 收藏CNKI翻译助手 | 广告服务 | 英文学术搜索
版权图标  2008 CNKI-中国知网
京ICP证040431号 互联网出版许可证 新出网证(京)字008号
北京市公安局海淀分局 备案号:110 1081725
版权图标 2008中国知网(cnki) 中国学术期刊(光盘版)电子杂志社