1) wavelet energy feature
小波能量特征
1.
A facial expression recognition method based on wavelet energy feature and Support Vector Machines(SVM)is developed.
首次提出了小波能量特征在表情识别中的应用。
2.
A facial expression recognition method based on wavelet energy feature and FLD is developed.
提出一种能量特征和Fisher线性判别法(FLD)相结合的面部表情识别方法,首次提出了小波能量特征在表情识别中的应用。
2) characteristics of wavelet packet energy
小波包能量特征
1.
To improve the recognition rate of sucker rod\'s defects,the composite characteristics including both the characteristics of wavelet packet energy and peak-to-peak values in time domain were applied to the recognition in combination with the SVM based on small samples.
为了提高抽油杆的缺陷识别率,将小波包能量特征和时域峰峰值特征组成的混合特征向量和基于小样本的支持向量机法应用于抽油杆的缺陷识别中。
3) wavelet-based attribute vector
小波特征向量
1.
Adequately the algorithm thinks about the grain feature of pixel and its neighborhood in brain CT image,subsequently constructs a multi-resolution wavelet-based attribute vector(WAV) of the pixel.
这种算法充分考虑了颅脑CT图像的像素点及其临域的纹理特征,通过进行小波变换建立对应于每个像素点的多分辨率小波特征向量,并以小波特征向量间的差异作为判别依据,在目标图像中标记非刚性配准所需的对应特征点。
4) wavelet packet energy eigenvector
小波包特征向量
1.
In order to diagnose the rotor fault precisely,this paper applies the resilient back propagation neural network and steepest descent back propagation neural network which based on wavelet packet energy eigenvector.
为精确诊断转子故障,采用了基于小波包能量特征向量的弹性BP神经网络和最速下降BP算法神经网络的故障诊断方法,对采集到的信号进行3层小波包分解,构造小波包特征向量,对样本进行3层BP网络训练,实现智能化故障诊断。
5) characterized wavelet
特征小波
1.
In order to get a characterized wavelet with expected properties of fault features extraction,by using the lifting scheme(LS),a new wavelet is constructed.
为了获得期望特性的特征小波,采用提升模式构造了一种新小波。
6) wavelet feature
小波特征
1.
At first,a four-level wavelet decomposition of the original spectrum is performed,and the wavelet coefficient at the fourth level,which mainly includes the information of spectral lines,is chosen as the wavelet feature of the spectrum.
首先,对原始光谱进行四级小波分解,选择主要包含谱线信息的第四级小波系数作为光谱的小波特征;然后,利用主分量分析对光谱的小波特征进行特征压缩,得到光谱的识别特征;最后,利用Fisher线性判别分析实现分类。
2.
This method consists of three main steps:First,after a wavelet transform with 5 scales on the spectra in a selected wavelength region,the wavelet features are extracted from the transformed coefficients on the 5th scale.
本文给出了一种自动识别M型星的新方法,该方法由以下主要步骤组成:①选取一定波长范围的光谱进行5层小波变换,从第5层小波系数中提取出小波特征;②利用小波特征检测M型星特征频率和吸收带位置;③根据特征频率和吸收带位置的检测结果进行M型星识别。
3.
We extracted wavelet feature fro.
首先对单个汉字的字符图像进行小波分解 ,在变换图像上提取小波特征 。
补充资料：分布和特征量统计(见统计分析)
分布和特征量统计(见统计分析)
fenbu he tezhengliang tongjj分布和特征量统计见统计分析。
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条