查询词典 feature vector

Research show that wavelet varied-grid feature vector is characterized by high-stable and high-distinguish. Based on this vector the apery cognitron has solved the harmony of single-classifier and multi-classifier and the harmony of multi-feature. The data shows that the recognition rate and reliability has been effective improve.

实验数据表明，小波变网格特征向量具有稳定性高、区分性强的特点，基于此的智能字符识别机解决了单、多分类器协调和特征协调问题，在应用快速二值化方法加强处理实时性的同时有效地提高了车牌字符的识别率和识别可靠性。

This paper proposed to use elliptical Gabor filter with least redundancy to convolute with palmprint,sub-bands with 4 scales and 6 directions are obtained,calculate the average and deviation of every sub-band,48D texture feature is extracted,and normalize the 48D feature in the whole database,finally use distance of absolute value to measure the difference between two feature vector.The result shows the arithmetic proposed by this paper has a little high retrieval accuracy.

本文采用最小冗余度的椭圆Gabor滤波器组对掌纹图像滤波，得到4个尺度6个方向的子带，计算每个子带的均值与方差，得到48维的纹理特征，在整个数据库中对48维特征进行归一化，最后采用绝对值距离衡量不同特征向量间的差异。

The dynamic and rectangular reseau of 8 , take the color histogram of every reseau , change their vector again , get the primitive feature vector of glossal image .

方法首先将舌图像划分成8×8的动态矩形网格，取每个网格的颜色直方图，再将它们向量化，得到舌图像的原始特征向量。

In this method, a feature vector with desirable characteristics including spatial locality, frequency and orientation selectivity is obtained by DT-CWT. Then, the dimension of the vector is linearly reduced by ONPP, thus effectively preserving the intrinsic neighborhood geometry of the vector and the global geometry.

先通过DT－CWT得到具有空间、频率以及方向特征的人脸特征表示，然后使用ONPP对特征向量进行线性降维，有效地保持了数据的局部与全局的几何特征，最后进行识别测试。

The method optimizes the features according to the class separable criterion of margin of within-class and among-class distance and selects the optimized feature vector combination based on four kinds of features,such as gray histogram feature,wavelet transform feature,gray level co-occurrence matrix feature and moment invariants feature,with 26 dimension feature vectors in all.

针对冷轧板带材常见表面缺陷图像识别的特点，提出了板带材表面缺陷多特征优化组合方法，该方法以直方图统计特征、小波变换特征、灰度共生矩阵特征、不变矩特征等4类特征共26维特征向量为基础，依据类间类内距离差的类别可分离性判据对特征进行优化，选出最优特征向量组合。

The adaption is done during operation and occurs by means of a displacement of the stored midpoint vector of the probability density distributions of hidden Markov models, in the direction of a known feature vector of sound expressions and in relationship to the hidden Markov models specially used.

适应是在运行中完成的，并且是通过隐含式－马而科夫－模型的概率密度分布的被存储的中心矢量的一个位移发生的，是在一个被识别的发音表达的特征矢量方向上并且是参照应用的隐含式－马而科夫－模型。

The multi-dimensional signals measured by sensors with a machine working under normal condition or fault condition, can be used to build Q statistic and T^2 statistic respectively to detect the state of the machine. Meanwhile, the feature vector is constructed by the Q value and the T^2 value, the geometrical distance between the normal feature vector and the feature vector H when the machine goes wrong is used to realize the fault location. The results show that the method is feasible.

利用多个传感器测量的异步电机多维信号参量，构建电机在正常工作和发生故障时的Q统计和T^2统计，以实现电机的状态检测；利用Q统计和T^2统计值构建电机的状态特征向量，通过比较度量当前电机的特征向量与电机发生故障时的特征向量H的几何距离来实现电机故障的定位与分离实验证明，该方法可以有效地实现故障的诊断与分离。

According to the different face representation mode, there are four identifying methods. They are the mode identifying method based on geometry feature vector, the feature vector identifying method based on algebra feature vector, the facial feature extraction method based on NN and design method of sorter.

根据表征方式的不同，人脸识别方法有：基于层次聚类的几何特征矢量模式识别法、基于代数特征矢量的特征矢量识别法、基于神经网络的人脸特征提取和分类器设计法。

The Karhunen-Loeve transform is used for feature reduction of the feature vectors and creating the subspaces. Then the distance between unknown-classification feature vector and each subspace is calculated to determine the class to which the vector belongs.

通过K-L变换，能有效降低特征空间的维数，形成各类别对应的特征子空间，然后分别计算待分类模式与各子空间的距离实现模式分类。

Instead of statistical description, a feature subspace with the base of some significant eigen vector extracted from covariance matrix is constructed to describe speech feature distribution of speaker. Distance metrics for measuring distance between input feature vector and subspace are also proposed for pattern matching.

说话人语音训练样本提取特征后在语音特征观察空间形成具有一定散度的分布，根据主元分析原理和分布散度提取主要散度本征向量作为基底构成说话人语音特征子空间，并通过测试语音特征矢量与子空间的距离测度进行模式匹配。

Methods: Five patients with parkinsonism or dystonia were assigned to general anesthesia using an modified endotracheal tube.

本实验依照人体实验之相关规定进行，五位患有帕金森氏症或肌张力异常的病人接受神经立体定位手术。

If you can benefit from this book, it is our honour.

如果您能从本书获益，这将是我们的荣幸。