NMI

A New Approach to Target Recognition Based on Image NMI Feature

基于图像NMI特征的目标识别新方法

Research of Binary Trade Mark Image Retrieval Method Based on NMI Invariable Feature

基于NMI不变特征的二值商标图像检索方法研究

Recognition of Alphabet Gesture Based on Orientation and High Order NMI Feature

高阶NMI值的字母手势识别

Target Recognition and Tracking Based on NMI Feature

基于NMI特征的目标识别与跟踪

Eye tracking based on Mean-Shift algorithm and NMI feature

基于Mean-Shift和NMI特征的人眼跟踪

A two-stage homotopy method was used to solve the NMI iteratively .

采用两步同伦法迭代来求解该非线性矩阵不等式（NMI）。

An alphabet gesture recognition algorithm based on orientation of gesture and high-order NMI feature of the image is presented .

提出了基于手势伸展方向以及手势图像高阶NMI值的特征向量进行识别分类的算法。

This paper has put forward a method of NMI feature combined with invariant feature to conceive the statistic feature of defective image .

文中提出了一种NMI特征和不变矩特征相结合的方法来构建缺陷图像的统计特征量。

We introduced NMI feature and invariant feature which meet geometrical invariance such as enlargement , translation and rotation .

其中NMI特征和不变矩特征两者均满足缩放、平移和旋转上的几何不变性。

Finally gives the relevance feedback algorithm of based NMI and entropy feature according to the trademark library . Experimental results show that it can improve retrieval accuracy .

最后结合商标图象库给出了基于NMI和信息熵的相关反馈算法，实验结果表明，可进一步提高检索精度。

IPSO-LMI hybrid algorithm transforms the solution procedure of NMI into an evolving optimization procedure , which takes the control performance as its target .

其中，IPSO-LMI混合算法将NMI问题的求解转换为一个与控制性能相关的进化寻优过程。

A definition of operation Latency of Network Management Interface ( NMI ), weighing the performance criterion of NMI on Latency , is proposed .

提出了网管接口时延性能的衡量指标&网管接口操作时延的定义。

This paper extracted wavelet energy feature , singular value feature , NMI features and wavelet moment based on the wavelet analysis respectively , and do a comparison recognition test .

本文分别在小波分析的基础上提取了能量特征，奇异值特征，NMI特征和小波矩特征，并做了对比识别试验。

On the basis of this , sufficient conditions are presented for the existence of the delay-dependent fuzzy controller described by nonlinear matrix inequality ( NMI ) .

在此基础上，给出了采用非线性矩阵不等式（NMI）表示的时滞相关模糊控制器存在的充分条件。

The definition of Centre of Mass and NMI feature is proposed and the principle and methods of Threshold calculation , Image segmentation , Target recognition and tracking are presented .

文章给出了运用连通线多级切割方法实现阈值求取、图像分割、目标识别与跟踪的技术技巧。

Considering the difficulty to solve NMI , the dissertation also proposes direct LMI algorithm and improved particle swarm optimization-LMI ( IPSO-LMI ) hybrid algorithm .

针对NMI求解困难的问题，提出了直接LMI算法和改进粒子群优化-LMI（IPSO-LMI）混合算法两种解决方案。

A new combined invariant moment was presented according to the characteristics of NMI 's feature and affine invariant moment proposed by Jan Flusser with their application conditions .

针对商标图像结构越来越复杂的特点，提出了一种基于联合不变矩形状特征的商标图像检索方法。

The CuCl / phen / NMI catalyst has a higher activity in the oxidative carbonylation of methanol and ethanol to MEC .

结果表明，CuCl/phen/NMI原位配合物催化剂对氧化羰化一步合成MEC反应具有较高的催化活性。

According to the feature of the trademark , this thesis proposes a two-grade retrieval algorithm , which is combined the NMI feature and the entropy feature of the trademark image .

结合商标图象的特点，本文给出了一种商标图象的NMI不变特性与信息熵特征相结合的分级检索算法。

Conclusion : The difference of Ala peak and the significant difference of mI / NmI can be helpful in the differential diagnosis between benign meningioma and haemangiopericytoma .

结论：Ala峰及mI峰的差异（尤其是mI/NmI）对良性脑膜瘤和血管外皮瘤的鉴别诊断有帮助。

Experimental results show that the NMI feature of image has the ability of anti-tonal and geometric distortions ( translation , rotation and scaling , TRS ), and its extraction method is simple .

实验结果表明：NMI特征具有抗灰度及TRS不变性，且提取方法简单，易于实现；

The mode specified using the given parameters described above should respect the following pattern : ^ ( [ nmi ] { 0,3 } ) | ( [ nmc ] { 0,3 } ) $ .

使用上述给定参数指定的模式应该遵循以下模式：^（[nmi]{0,3}）（[nmc]{0,3}）$。

In this paper , a new method of Image Segmentation , namely Consecutive Line Multilevel Segmentation , and the algorithm of Target Recognition and Tracking based on Normalized Moment of Inertia ( NMI ) feature are introduced .

本文提出一种全新的图像分割方法&连通线多级切割方法，并在此基础上建立图像NMI特征的目标识别与跟踪算法。

Focusing on the two feature recognition methods , NMI ( Normalized Moment of Inertia ) feature recognition and moment invariant feature recognition , through experiments , writer analyzes the difference in rotation invariability , scaling invariability and random noise invariability of the two methods .

本文针对NMI（归一化转动惯量）特征识别和仿射不变矩特征识别二种图像特征识别方法，通过实验分析该二种识别方法在旋转不变性、缩放不变性、随机噪声不变性上的差异。