The thesis uses the method to train face feature classifier, to get the face feature points and build face feature triangle that uses eyes and mouth as vertexes.
本文采用该算法训练人脸面部特征检测器，提取区域的几何中心进行面部特征点定位，获取以双眼和嘴巴为特征顶点的人脸特征三角形。
Instead, the names of the input and output pins on the actions are labeled by a parameter, variable, or structural feature in the context classifier (the class owning the activity) that is in scope.
相反，操作上输入与输出的名字，会标上范围内背景标识符(拥有活动的类)中的参数、变量或者结构性特性。
Experimental results have shown that our feature extraction and recognition method is very effective, and the designed classifier has high recognition performance.
实验结果表明：我们的特征抽取和识别方法非常有效，由此设计的分类器具有较高的识别率。
The contents in the paper include acoustic image preprocessing, feature extraction of texture and shape, and classifier design.
内容涉及声图像的预处理、纹理和形状特征的提取，以及分类器的设计等。
In this paper, we review the present research status and some key techniques in this field, including the property of HRRP, preprocessing methods, feature extraction and classifier design.
该文详细讨论了基于HRRP的雷达自动目标识别的关键技术及研究现状，包括雷达hrrp的特性、预处理方法、特征提取方法及分类器设计方法等。
Feature extraction of targets radiated noise and design of targets classifier are key technique of passive sonar target recognition system.
目标噪声特征提取和目标分类器设计是被动声呐目标识别系统的关键技术。
Feature selection and parameters optimization of the fault classifier can enhance the fault diagnosis accuracy.
在机械故障诊断中，特征选择和分类器的参数优化都可以提高诊断精度。
Feature extraction of targets radiated noise and design of targets classifier are key issues of passive sonar target recognition system.
目标噪声特征提取和目标分类器设计是被动声纳目标识别系统的关键技术。
The test shows that multi-scale Lempel-Ziv complexity can be used as an image classification method or as a feature of image classifier.
该结果说明：不同尺度下复杂性的差异可以作为图像分类的新方法或者作为现有分类器的特征。
Then, the classifier based on the normalized template feature is applied to the samples rejected by the former.
然后由基于数字规范化模板特征的分类器对前一级分类器的拒识样本分类。
Feature selection is an important process in a target classification program and directly affects the design and performance of the classifier.
特征选择是目标分类的一项重要步骤，直接影响到分类器的设计和性能。
In this paper, we investigate enhancement of naive Bayes classifier using feature weighting technique.
该文利用特征加权技术来增强朴素贝叶斯分类器。
For improving the performance of multiple classifier system, a novel method of ensemble feature selection is proposed based on generalized rough set.
为改善多分类器系统的分类性能，提出了基于广义粗集的集成特征选择方法。
Feature selection and classifier parameter optimization are two important aspects for improving classifier performance and are solved separately traditionally.
特征选择及分类器参数优化是提高分类器性能的两个重要方面，传统上这两个问题是分开解决的。
This paper presents a multiclass neural network classifier to learn disjunctive fuzzy information in the feature space.
本篇论文提出一个类神经网路分类器来学习多类的分离模糊资讯。
The algorithm used weighted templates to structure each weak learning classifier, which overcame the shortcoming of structuring classifier by using a single feature.
在该演化算法中，采取训练正反类样本加权模板的方法来构造各个弱学习分类器，克服了常规的基于单一特征构造弱分类器的不足。
For the best feature, we also use the classifier based on KCCA to reclassify it.
对检测率最高的特征，我们用基于核典型相关分析的分类器重新分类。
The study of steganalysis mainly consists feature extraction and classifier selection and design.
隐藏检测的研究主要包括特征提取和分类器的选择与设计两个部分。
To solve the problem of false positive in micro-calcification detection, a double-layer support vector classifier model with reject feature is proposed.
为克服微钙化点检测中假阳性高的缺点，本文构造了一种带拒识能力的双层支持向量模型分类器用于钙化点检测。
Feature selection is an important issue in the fields of machine learning and pattern recognition. The effectiveness of feature directly affects the design and performance of the classifier.
特征选择问题是机器学习和模式识别中的一个重要问题，特征的优劣直接影响分类器的设计和性能。
Measure some feature of one image and take it to classifier, this is an important step of pattern recognition.
把某一图像的某种特征进行度量并交给分类器，是模式识别的重要环节。
The techniques of feature extraction, feature selection and design of classifier for passive sonar target recognition are reviewed.
文章对被动声纳目标识别的特征提取、特征选择和分类器设计方面进行了回顾。
Usually image recognition based on neural networks needs feature extraction, and then the features extracted are delivered to the neural network classifier.
神经网络用于图像识别一般都要提取图像特征，然后把提取好的图像特征送入神经网络识别器进行识别。
The main idea of which consists of three parts: the discriminating feature analysis of the images, the statistical modeling of face and non-face classes, and the Bayes classifier for face detection.
研究了人脸检测的贝叶斯特征判别法，该方法包括三个部分：原始图像的特征判别分析、人脸区和其它区的统计建模以及贝叶斯分类器。
Then current recognition technologies are roughly introduced and classified according to different method of feature extraction and classifier design.
重点按照不同的特征提取和分类器设计方法对表情识别技术进行了综述。
The proposed method optimizes spectral information by feature extraction and reduces the spectral noise. The classifier performance is improved.
该方法利用特征提取优化了光谱信息，降低了谱间噪声，提高了分类器的性能。
Eventually, the compatibility between the generated rules and patterns was used to construct a set of feature vectors, which were used to generate a classifier.
最后，通过计算规则和模式之间的兼容性指标来构造特征向量，构建支持向量机的分类器模型。
The main contribution of this dissertation includes four aspects. They are instantaneous parameters extraction, fuzzy feature selection, single classifier design and combined classifier design.
本文主要工作体现在瞬时参数的提取、模糊特征选择、单个分类器设计和组合分类器设计这四个方面。
It does not have to design the complexity classifier in the traditional recognition algorithm after feature extraction, and simplifies the recognition process.
无需传统识别算法中特征提取之后复杂的分类器设计，简化了识别流程。
The experimental comparisons show that this algorithm outperforms traditional KPCA and K-Nearest Neighbor classifier on both feature extraction and classification.
通过实验比对可知该算法效果在特征提取和分类方面均优于传统核主成分分析法以及最近邻分类器。
应用推荐